diff --git a/.github/workflows/consolidated-tests-ci.yml b/.github/workflows/consolidated-tests-ci.yml index 489ee4ca08..afad1b6c46 100644 --- a/.github/workflows/consolidated-tests-ci.yml +++ b/.github/workflows/consolidated-tests-ci.yml @@ -373,11 +373,10 @@ jobs: tests/test_bad_mappings_redirect.py \ tests/test_prefetch_snapshot_scope.py \ tests/test_gemma_2b_mapper_key.py \ - --deselect 'tests/utils/test_attention_masks.py::test_run_attention_flash_varlen_receives_window_and_softcap' - # The deselected test monkeypatches flash_attn_varlen_func, which is - # only bound on the module when `flash_attn` is importable. flash_attn - # requires CUDA + dev toolchain, which the CPU-only ubuntu-latest - # runner does not have. The other Bucket-A tests pass cleanly. + tests/test_raw_text_json_loading.py + # test_run_attention_flash_varlen_receives_window_and_softcap was deselected + # until attention_dispatch.py predefined flash_attn_varlen_func as None; it + # monkeypatches that name, so it no longer needs flash_attn on this runner. - name: unsloth_zoo @ ${{ env.UNSLOTH_ZOO_REF }} — full pytest (CPU) # 106 of 111 test_* in unsloth_zoo are CPU-only. The two CUDA-skip diff --git a/install.sh b/install.sh index 376daa8fab..fc9aa0a431 100755 --- a/install.sh +++ b/install.sh @@ -321,10 +321,25 @@ _gfx906_bnb_prune() { || "$_VENV_PY" -m pip uninstall -y bitsandbytes >/dev/null 2>&1 || true } -# Install bitsandbytes on AMD ROCm hosts. Uses the continuous-release_main -# wheel for the ROCm 4-bit GEMV fix (bnb PR #1887, post-0.49.2); bnb <= 0.49.2 -# NaNs at decode shape on every AMD GPU. Falls back to PyPI >=0.49.1 if the -# pre-release URL is unreachable. Drop the pin once bnb 0.50+ ships on PyPI. +# Install bitsandbytes on AMD ROCm hosts. bnb <= 0.49.2 NaNs at 4-bit decode +# shape on every AMD GPU; the fix (bnb #1887) ships in continuous-release_main +# and, on PyPI, first in 0.50.0. Keep this floor in step with the amd extra in +# pyproject.toml and studio/install_python_stack.py. +_BNB_ROCM_PYPI_FALLBACK="bitsandbytes>=0.50.0" +# bitsandbytes ships no ROCm binary in its aarch64 wheel at any version: the PyPI +# 0.50.0 and continuous-release_main aarch64 wheels both carry only +# libbitsandbytes_cpu.so plus CUDA variants. So neither install path below gives +# aarch64 a 4-bit backend, and the messages must not claim one. Cf. gfx906. +_bnb_rocm_arch_has_binary() { + case "$_ARCH" in + aarch64|arm64) return 1 ;; + *) return 0 ;; + esac +} +_warn_bnb_no_rocm_binary() { + _bnb_rocm_arch_has_binary && return 0 + substep "[WARN] aarch64: bitsandbytes ships no ROCm kernels on this arch; 4-bit QLoRA needs a source build -- https://docs.unsloth.ai/get-started/install-and-update/amd" "$C_WARN" +} _install_bnb_rocm() { _label="$1" _venv_py="$2" @@ -339,9 +354,8 @@ _install_bnb_rocm() { _bnb_whl_url="" ;; esac - # uv rejects the continuous-release_main bitsandbytes wheel because the - # filename version (1.33.7rc0) does not match the embedded metadata version - # (0.50.0.dev0). pip accepts the mismatch, so bootstrap pip and use it. + # uv rejects the pre-release wheel: filename version (1.33.7rc0) does not + # match metadata (0.50.x.dev0). pip accepts it, so bootstrap pip and use it. if ! "$_venv_py" -m pip --version >/dev/null 2>&1; then if ! run_maybe_quiet "$_venv_py" -m ensurepip --upgrade; then run_maybe_quiet uv pip install --python "$_venv_py" pip || \ @@ -357,6 +371,7 @@ _install_bnb_rocm() { --retries 8 --timeout 90 \ "$_bnb_whl_url" >"$_bnb_log" 2>&1; then rm -f "$_bnb_log" + _warn_bnb_no_rocm_binary return 0 fi _bnb_rc=$? @@ -365,10 +380,17 @@ _install_bnb_rocm() { fi rm -f "$_bnb_log" step "warning" "$_label (pre-release) failed (exit code $_bnb_rc)" "$C_WARN" >&2 - substep "[WARN] bnb pre-release install failed; falling back to PyPI (4-bit decode broken on ROCm)" "$C_WARN" + if _bnb_rocm_arch_has_binary; then + substep "[WARN] bnb pre-release install failed; falling back to PyPI $_BNB_ROCM_PYPI_FALLBACK, which carries the ROCm 4-bit fix" "$C_WARN" + else + substep "[WARN] bnb pre-release install failed; falling back to PyPI $_BNB_ROCM_PYPI_FALLBACK" "$C_WARN" + fi fi run_install_cmd "$_label (pypi fallback)" "$_venv_py" -m pip install \ - --force-reinstall --no-cache-dir --no-deps "bitsandbytes>=0.49.1" + --force-reinstall --no-cache-dir --no-deps "$_BNB_ROCM_PYPI_FALLBACK" + _bnb_pypi_rc=$? + _warn_bnb_no_rocm_binary + return $_bnb_pypi_rc } if [ "$_next_is_package" = true ]; then @@ -778,8 +800,17 @@ _smart_apt_install() { return 0 fi - # In Tauri mode, report needed packages and exit — Rust handles elevation + # Optional callers never elevate, in any mode: nothing on the consumer path + # builds anything, so neither the terminal sudo prompt below nor the Tauri + # NEED_SUDO dialog (whose Cancel leaves the user not installed) may gate the + # run over unused tools. The caller falls through to prebuilt llama.cpp. + # Required packages such as curl still escalate. + if [ "${_SMART_APT_OPTIONAL:-false}" = true ]; then + return 2 + fi + if [ "$TAURI_MODE" = true ]; then + # Report needed packages and exit — Rust handles elevation. tauri_log "NEED_SUDO" "$_STILL_MISSING" exit 2 fi @@ -1976,67 +2007,142 @@ _maybe_reroute_strixhalo_to_2404() { _maybe_reroute_strixhalo_to_2404 || true # ── Check system dependencies ── -# cmake/git are only needed to *build* llama.cpp from source. Unsloth downloads a -# prebuilt by default, and setup.sh self-skips the source build when they're -# absent -- so macOS doesn't block on cmake (requiring it would force a manual -# Homebrew install). Linux keeps requiring them; its package manager has them. tauri_log "STEP" "Checking system dependencies" +# Without the Xcode CLT, macOS still ships /usr/bin/git as a stub that errors and pops +# a GUI dialog, so `command -v git` is not enough -- only running it tells the truth. +_has_working_git() { + command -v git >/dev/null 2>&1 || return 1 + git --version >/dev/null 2>&1 +} + +# macOS system-dependency check. A function so tests/sh can sed-extract it; the old +# inline form was untestable, which is why this gate shipped broken. +# +# The consumer install needs no developer toolchain: uv is a prebuilt binary, CPython +# is uv-managed, llama.cpp/whisper.cpp/Node are prebuilt downloads, and triton is +# skipped on macOS. Only `--local` needs git, for the unsloth-zoo git+https URL. +_check_macos_deps() { + _clt_missing=false + xcode-select -p >/dev/null 2>&1 || _clt_missing=true + + if [ "$STUDIO_LOCAL_INSTALL" = true ] && ! _has_working_git; then + echo "" + step "deps" "git is required for --local installs" "$C_ERR" + substep "--local installs unsloth-zoo from git+https://github.com/unslothai/unsloth-zoo," + substep "which needs a working git. Install the Xcode Command Line Tools:" + substep " xcode-select --install" + substep "Then re-run this script. A normal (non---local) install needs no compiler" + substep "and no git -- it uses prebuilt binaries and wheels only." + tauri_log "NEED_XCODE_CLT" "git" + return 1 + fi + + if [ "$_clt_missing" = true ]; then + # Not fatal, and no GUI dialog: firing xcode-select --install and exiting is + # what stranded clean Macs. + step "deps" "no Xcode Command Line Tools (not required)" "$C_WARN" + substep "Unsloth installs prebuilt binaries and wheels, so no compiler is needed." + substep "Install them only for a llama.cpp source build: xcode-select --install" + elif command -v cmake >/dev/null 2>&1; then + step "deps" "all system dependencies found" + else + # cmake is only for a source build, so its absence is not fatal. + step "deps" "using prebuilt llama.cpp (cmake not found)" "$C_WARN" + substep "Install cmake only if you want a source build: brew install cmake" + fi + return 0 +} + +# Linux/WSL system-dependency check. Same split as macOS, and a function for the same +# reason: tests/sh can extract it. +# +# Only a download transport is required. cmake, gcc and the libcurl headers exist +# solely for a llama.cpp source build the consumer path never does -- unslothai/ +# llama.cpp publishes linux-x64/arm64 prebuilts for cpu, cuda12, cuda13, rocm and +# vulkan. Requiring them turned every non-apt distro into a hard exit 1 over unused +# tooling. git follows macOS: --local only. +_check_linux_deps() { + _transport_missing=false + if ! command -v curl >/dev/null 2>&1 && ! command -v wget >/dev/null 2>&1; then + _transport_missing=true + fi + + # Wanted, never required: git fetches the triton_kernels git+https requirement (a + # training speedup), the rest serve the optional source build. Warn, never stop. + _optional_missing="" + command -v cmake >/dev/null 2>&1 || _optional_missing="$_optional_missing cmake" + _has_working_git || _optional_missing="$_optional_missing git" + command -v gcc >/dev/null 2>&1 || _optional_missing="$_optional_missing build-essential" + command -v curl-config >/dev/null 2>&1 || _optional_missing="$_optional_missing libcurl4-openssl-dev" + # Parameter expansion, not `sed`: sed may be absent on a minimal image, and a + # failed `$(... | sed ...)` yields "" -- "all found" on a machine that has none. + _optional_missing="${_optional_missing# }" + + if [ "$STUDIO_LOCAL_INSTALL" = true ] && ! _has_working_git; then + echo "" + step "deps" "git is required for --local installs" "$C_ERR" + substep "--local installs unsloth-zoo from git+https://github.com/unslothai/unsloth-zoo," + substep "which needs git. Install it with your package manager, then re-run." + substep "A normal (non---local) install needs no git and no compiler." + return 1 + fi + + # The one fatal case: nothing can be downloaded. apt is the only distro family we + # can drive unattended. + if [ "$_transport_missing" = true ]; then + if command -v apt-get >/dev/null 2>&1; then + echo "" + step "deps" "missing: curl" "$C_WARN" + substep "Needed to download uv, Python and the prebuilt inference engine." + _smart_apt_install curl + echo "" + else + echo "" + step "deps" "missing: curl (or wget)" "$C_ERR" + substep "Unsloth needs one of them to download uv, Python and the prebuilt" + substep "inference engine. Install one, then re-run setup:" + substep " Fedora/RHEL: sudo dnf install curl" + substep " Arch: sudo pacman -S --needed curl" + substep " openSUSE: sudo zypper install curl" + return 1 + fi + fi + + # Try apt for the optional set too; failing only costs the features warned about + # below. + if [ -n "$_optional_missing" ] && command -v apt-get >/dev/null 2>&1; then + step "deps" "installing optional build tools: $_optional_missing" "$C_DIM" + # Subshell because _smart_apt_install exits rather than returns, so `|| true` + # alone would not catch it. _SMART_APT_OPTIONAL suppresses every escalation + # path, so no install hinges on a prompt for tools nothing here needs. + ( _SMART_APT_OPTIONAL=true; _smart_apt_install $_optional_missing ) || true + _optional_missing="" + command -v cmake >/dev/null 2>&1 || _optional_missing="$_optional_missing cmake" + _has_working_git || _optional_missing="$_optional_missing git" + command -v gcc >/dev/null 2>&1 || _optional_missing="$_optional_missing build-essential" + command -v curl-config >/dev/null 2>&1 || _optional_missing="$_optional_missing libcurl4-openssl-dev" + _optional_missing="${_optional_missing# }" + fi + + if [ -n "$_optional_missing" ]; then + step "deps" "using prebuilt llama.cpp (missing: $_optional_missing)" "$C_WARN" + substep "Not required to run: Unsloth downloads a prebuilt inference engine." + case " $_optional_missing " in + *" git "*) substep "Without git the triton kernels training speedup is skipped." ;; + esac + else + step "deps" "all system dependencies found" + fi + return 0 +} + case "$OS" in macos) - # Xcode Command Line Tools provide the C/C++ compiler and git. - if ! xcode-select -p >/dev/null 2>&1; then - echo "" - echo "==> Xcode Command Line Tools are required." - echo " Installing (a system dialog will appear)..." - xcode-select --install /dev/null || true - echo " After the installation completes, please re-run this script." - exit 1 - fi - # cmake is only needed for a source build; the default prebuilt path - # doesn't use it, so its absence is not fatal -- no Homebrew prerequisite. - if command -v cmake >/dev/null 2>&1; then - step "deps" "all system dependencies found" - else - step "deps" "using prebuilt llama.cpp (cmake not found)" "$C_WARN" - substep "Install cmake only if you want a source build: brew install cmake" - fi + _check_macos_deps || exit 1 ;; linux|wsl) - MISSING="" - command -v cmake >/dev/null 2>&1 || MISSING="$MISSING cmake" - command -v git >/dev/null 2>&1 || MISSING="$MISSING git" - # curl or wget is needed for downloads; check both - if ! command -v curl >/dev/null 2>&1 && ! command -v wget >/dev/null 2>&1; then - MISSING="$MISSING curl" - fi - command -v gcc >/dev/null 2>&1 || MISSING="$MISSING build-essential" - # libcurl dev headers for llama.cpp HTTPS support - command -v curl-config >/dev/null 2>&1 || MISSING="$MISSING libcurl4-openssl-dev" - - MISSING=$(echo "$MISSING" | sed 's/^ *//') - if [ -n "$MISSING" ]; then - echo "" - step "deps" "missing: $MISSING" "$C_WARN" - substep "These are needed to build the GGUF inference engine." - if command -v apt-get >/dev/null 2>&1; then - _smart_apt_install $MISSING - else - echo " Automatic system package installation is supported on apt-based" - echo " Linux distributions (Ubuntu/Debian) only. Please install the" - echo " missing dependencies with your package manager, then re-run setup:" - echo " $MISSING" - echo "" - echo " Examples:" - echo " Fedora/RHEL: sudo dnf install cmake git gcc gcc-c++ make libcurl-devel" - echo " Arch: sudo pacman -S --needed cmake git base-devel curl" - echo " openSUSE: sudo zypper install cmake git gcc gcc-c++ make libcurl-devel" - exit 1 - fi - echo "" - else - step "deps" "all system dependencies found" - fi + _check_linux_deps || exit 1 ;; esac diff --git a/pyproject.toml b/pyproject.toml index 62623499d6..7359a51fa6 100644 --- a/pyproject.toml +++ b/pyproject.toml @@ -1257,8 +1257,11 @@ intel = [ ] amd = [ "unsloth[huggingfacenotorch]", - "bitsandbytes>=0.49.1 ; ('linux' in sys_platform) and (platform_machine == 'AMD64' or platform_machine == 'x86_64' or platform_machine == 'aarch64')", - "bitsandbytes>=0.49.1 ; (sys_platform == 'win32') and (platform_machine == 'AMD64' or platform_machine == 'x86_64')", + # 4-bit decode is unreliable on ROCm before 0.50.0, the first PyPI release + # carrying the full path: blocksize/warp decoupling (bnb #1887), fused SIMT + # GEMM on RDNA (#1979), RDNA3/4 workgroup fix (#2012). + "bitsandbytes>=0.50.0 ; ('linux' in sys_platform) and (platform_machine == 'AMD64' or platform_machine == 'x86_64' or platform_machine == 'aarch64')", + "bitsandbytes>=0.50.0 ; (sys_platform == 'win32') and (platform_machine == 'AMD64' or platform_machine == 'x86_64')", ] rocm702-torch280 = [ "unsloth[amd]", diff --git a/studio/backend/core/inference/llama_admission.py b/studio/backend/core/inference/llama_admission.py index db9a5d8ce4..7bf0dd7429 100644 --- a/studio/backend/core/inference/llama_admission.py +++ b/studio/backend/core/inference/llama_admission.py @@ -58,6 +58,80 @@ DEFAULT_ADMISSION_QUEUE_PER_SLOT = 16 DEFAULT_ADMISSION_MIN_QUEUE = 64 +def _executor_workers() -> int: + """Threads asyncio's default executor runs to_thread work on. + + Mirrors ThreadPoolExecutor's own default sizing, which is what + ``run_in_executor(None, ...)`` builds. 3.13 sizes it from + ``process_cpu_count()``, which honours CPU affinity and cgroup quotas; + ``cpu_count()`` would budget from the whole host inside a one-core container. + """ + cpus = getattr(os, "process_cpu_count", os.cpu_count)() or 1 + return min(32, cpus + 4) + + +def _executor_reserve(workers: int) -> int: + """Threads kept clear of parked approvals, for generation steps, stream + teardown and unrelated to_thread work. Scaled rather than flat: a flat count + would leave a 5-worker executor (one usable CPU) no budget at all. + """ + return max(2, workers // 8) + + +def _max_parked(capacity: int) -> int: + """How many holders may sit on an approval prompt with their slot given back. + + A pending prompt parks an executor thread (the loop blocks inside + to_thread(next, gen)) whether or not it parked its slot, the pool already + permits `capacity` of those, and every park admits one more, so budget only + what the executor has left over. Zero on a backend whose --parallel alone + fills it: the prompt then holds its slot, as it did before parking existed. + """ + workers = _executor_workers() + spare = workers - _executor_reserve(workers) - max(0, capacity) + # A quarter of the executor, floored at two while `spare` allows: a quarter of + # five is one, and one park cannot cover the two simultaneous prompts #7455 + # exists for. + return max(0, min(max(2, workers // 4), spare)) + + +# Process-wide, not per queue: there is one executor, and base_url takes a fresh +# port on every load, so a per-queue budget would hand the same allowance to each +# backend and to every reload, blind to the approvals parked on the old queue. +_PARK_LOCK = threading.Lock() +_parked_total = 0 + + +def _claim_park(limit: int) -> bool: + global _parked_total + with _PARK_LOCK: + if _parked_total >= limit: + return False + _parked_total += 1 + return True + + +def _drop_park() -> None: + global _parked_total + with _PARK_LOCK: + _parked_total = max(0, _parked_total - 1) + + +def _live_capacity(current: "LlamaAdmissionQueue") -> int: + """Slots across every backend still serving requests. + + One queue's capacity is the wrong denominator for a budget sized against the + one executor: a reload drains the old queue alongside the new one, and + prompts on both park threads. Idle queues hold nothing and are about to be + evicted. + """ + with _QUEUES_LOCK: + queues = list(_QUEUES.values()) + # is_idle takes each queue's own lock, so never while holding _QUEUES_LOCK. + total = sum(queue._capacity for queue in queues if queue is current or not queue.is_idle()) + return total if any(queue is current for queue in queues) else total + current._capacity + + @dataclass(frozen = True, **_SLOTS) class LlamaAdmissionConfig: enabled: bool = DEFAULT_ADMISSION_ENABLED @@ -214,7 +288,7 @@ class _Waiter: class LlamaAdmissionLease: - __slots__ = ("_queue", "_slot", "_released", "_release_lock", "_parked") + __slots__ = ("_queue", "_slot", "_released", "_release_lock", "_parked", "_budgeted") def __init__( self, @@ -226,27 +300,52 @@ class LlamaAdmissionLease: self._released = False self._release_lock = threading.Lock() self._parked = False + self._budgeted = False @property def slot(self) -> Optional[int]: """Pool slot this lease holds, or None when admission is disabled.""" return self._slot - def park(self) -> None: + def park(self) -> bool: """Hand the slot back while this holder waits on something off the GPU. A run stopped on a tool approval prompt is not decoding, so holding its slot would let unanswered prompts fill the pool while llama-server idles. The lease itself stays valid: releasing it after a park is still correct. + + False when the park budget is spent and nothing was given back: the + caller keeps its slot across the prompt, as it did before parking + existed. Slower for whoever is behind it, but each freed slot admits + another run that can park too, on the executor the generators run on. """ queue = self._queue - slot = None with self._release_lock: if queue is None or self._released or self._parked: - return + return False + # Under the lease lock so the decision and the handover cannot split. + # Nothing takes the queue lock then a lease lock, so this order is + # the only one in play. + if not queue.try_park(self._slot): + return False self._parked = True - slot, self._slot = self._slot, None - queue.park(slot) + self._budgeted = True + self._slot = None + return True + + def _drop_budget(self) -> None: + """Give the executor budget back now the prompt wait is over. + + Separate from the queue's parked count, which lasts until the slot is + back: the executor thread is free the moment the answer arrives. Holding + the budget until the resume lands would refuse someone else's park for a + finished wait, and that someone holds the slot the resumer wants. + """ + with self._release_lock: + if not self._budgeted: + return + self._budgeted = False + _drop_park() def unpark(self) -> None: """Drop the parked state without reclaiming a slot. @@ -259,6 +358,7 @@ class LlamaAdmissionLease: if not self._parked: return self._parked = False + self._drop_budget() if self._queue is not None: self._queue.unpark() @@ -278,6 +378,9 @@ class LlamaAdmissionLease: queue = self._queue if queue is None or not self._parked: return + # Before the wait, not after: the prompt is answered, so this holder is + # already off the executor and must not keep anyone else off it. + self._drop_budget() slot = await queue.acquire_parked_slot(cancel_event = cancel_event, poll_s = poll_s) stranded = None with self._release_lock: @@ -304,6 +407,7 @@ class LlamaAdmissionLease: self._released = True queue = self._queue parked, self._parked = self._parked, False + self._drop_budget() if queue is not None: if parked: queue.unpark() @@ -513,12 +617,20 @@ class LlamaAdmissionQueue: self._release_slot_locked(slot) self._grant_waiters_locked() - def park(self, slot: Optional[int]) -> None: - """Return a parked holder's slot to the pool. See ``LlamaAdmissionLease.park``.""" + def try_park(self, slot: Optional[int]) -> bool: + """Return a parked holder's slot to the pool. See ``LlamaAdmissionLease.park``. + + False leaves the slot with its holder, so a refused park costs nothing to + undo. The per-queue count is only what ``is_idle`` reads; the budget and + the capacity it is sized from are both process-wide. + """ + if not _claim_park(_max_parked(_live_capacity(self))): + return False with self._lock: self._parked += 1 self._release_slot_locked(slot) self._grant_waiters_locked() + return True def unpark(self) -> None: with self._lock: @@ -684,5 +796,10 @@ def get_llama_admission_queue(key: str) -> LlamaAdmissionQueue: def reset_llama_admission_queues() -> None: + global _parked_total with _QUEUES_LOCK: _QUEUES.clear() + # The budget outlives the queues it was claimed against, so dropping them + # without it leaks the count and shrinks the budget for good. + with _PARK_LOCK: + _parked_total = 0 diff --git a/studio/backend/core/inference/llama_cpp.py b/studio/backend/core/inference/llama_cpp.py index f76afce9f4..144aa1fd37 100644 --- a/studio/backend/core/inference/llama_cpp.py +++ b/studio/backend/core/inference/llama_cpp.py @@ -92,6 +92,7 @@ from utils.subprocess_compat import ( from utils.process_lifetime import child_popen_kwargs as _child_popen_kwargs from core.inference.tool_call_parser import ( MAX_ACT_REPROMPTS as _MAX_REPROMPTS, + NUDGE_TOOL_CALLS_STATUS as _NUDGE_TOOL_CALLS_STATUS, REPROMPT_MAX_CHARS as _REPROMPT_MAX_CHARS, is_short_intent_without_action as _is_short_intent_without_action, reprompt_to_act_message as _reprompt_to_act_message, @@ -1697,9 +1698,20 @@ def _kv_unified_from_args( return enabled -def _flash_attn_enabled_from_args(args: Optional[Iterable[str]], default: bool = True) -> bool: - """Resolve llama.cpp's last-wins flash-attention CLI setting.""" +def _flash_attn_enabled_from_args( + args: Optional[Iterable[str]], + default: bool = True, + env: Optional[Mapping[str, str]] = None, +) -> bool: + """Resolve llama.cpp's environment and last-wins flash-attention settings.""" enabled = default + # llama.cpp applies LLAMA_ARG_FLASH_ATTN before parsing argv (arg.cpp set_env), + # so the CLI still wins. --flash-attn has no args_neg, so no LLAMA_ARG_NO_ twin. + value = (os.environ if env is None else env).get("LLAMA_ARG_FLASH_ATTN") + if value in _LLAMA_ARG_FALSE_VALUES: + enabled = False + elif value in _LLAMA_ARG_TRUE_OR_AUTO_VALUES: + enabled = True values = [str(arg) for arg in args] if args else [] for i, raw in enumerate(values): if _flag_name(raw) not in {"-fa", "--flash-attn"}: @@ -2181,6 +2193,8 @@ class LlamaCppBackend: self._effective_context_length: Optional[int] = None self._max_context_length: Optional[int] = None self._effective_parallel_slots: int = 1 + # --parallel the last load asked for, before any fit-time reduction. + self._requested_n_parallel: int = 1 self._chat_template: Optional[str] = None self._chat_template_override: Optional[str] = None self._supports_reasoning: bool = False @@ -2417,6 +2431,17 @@ class LlamaCppBackend: slots = 1 return max(1, slots) + @property + def requested_parallel_slots(self) -> int: + """--parallel the last load asked for, before any fit-time reduction. + The reload dedupe compares requested-vs-requested (like requested_n_ctx); + the effective count would reload forever after a fitter reduction.""" + try: + slots = int(getattr(self, "_requested_n_parallel", 1)) + except (TypeError, ValueError): + slots = 1 + return max(1, slots) + @property def max_context_length(self) -> Optional[int]: """Return the largest context that fits on this hardware at load time. @@ -2442,6 +2467,8 @@ class LlamaCppBackend: def _reset_effective_parallel_slots(self) -> None: self._effective_parallel_slots = 1 + # Cleared with the effective count so a stale value can't skew the dedupe. + self._requested_n_parallel = 1 @staticmethod def _read_rss_bytes(pid: int) -> Optional[int]: @@ -6787,6 +6814,7 @@ class LlamaCppBackend: chat_template_override = chat_template_override, extra_args = extra_args, is_vision = is_vision, + n_parallel = n_parallel, preserve_multi_gpu_on_layer = preserve_multi_gpu_on_layer, ): logger.info( @@ -9038,7 +9066,8 @@ class LlamaCppBackend: int(self._DEFAULT_N_UBATCH if _effective_ubatch is None else _effective_ubatch), ) self._flash_attn_enabled = ( - _flash_attn_enabled_from_args(_last_spawn_cmd) and self._architecture != "grok" + _flash_attn_enabled_from_args(_last_spawn_cmd, env = env) + and self._architecture != "grok" ) self._effective_cache_types = _effective_main_cache_types( _last_spawn_cmd, @@ -9066,6 +9095,8 @@ class LlamaCppBackend: self._extra_args = list(extra_args) self._extra_args_source = (model_identifier, hf_variant) self._requested_n_ctx = int(n_ctx) + # Local n_parallel may have been reduced above; the snapshot has the ask. + self._requested_n_parallel = max(1, int(_pending_load_kwargs["n_parallel"])) # Commit the known-good snapshot + whether MTP+tensor is live, then # watch this load for a mid-generation crash. self._last_load_kwargs = _pending_load_kwargs @@ -9478,6 +9509,7 @@ class LlamaCppBackend: tensor_split: Optional[List[float]] = None, gpu_ids: Optional[List[int]] = None, mtp_draft_path: Optional[str] = None, + n_parallel: int = 1, preserve_multi_gpu_on_layer: bool = False, ) -> bool: """True iff the live server already satisfies these load kwargs. @@ -9542,6 +9574,10 @@ class LlamaCppBackend: # A GPU-memory-mode flip (Unsloth / manual) must always reload. if self._gpu_memory_mode != gpu_memory_mode: return False + # Requested-vs-requested (like n_ctx): comparing the effective count + # would reload forever whenever the fitter launched fewer slots. + if self._requested_n_parallel != max(1, int(n_parallel)): + return False # Manual: a layer-count change always reloads (covers Auto(-1) <-> a # pinned count); MoE/split only matter with an explicit offload. if gpu_memory_mode == "manual" and ( @@ -12384,7 +12420,10 @@ class LlamaCppBackend: _it_r = _iter_timings or {} _accumulated_predicted_ms += _it_r.get("predicted_ms", 0) _accumulated_predicted_n += _it_r.get("predicted_n", 0) + # Blank first (the route resets its text cursor only on an + # empty status), then the badge so the retry is not a hang. yield {"type": "status", "text": ""} + yield {"type": "status", "text": _NUDGE_TOOL_CALLS_STATUS} continue if _forced_tool_call_pending: diff --git a/studio/backend/core/inference/llama_server_args.py b/studio/backend/core/inference/llama_server_args.py index 2ecd7e3e2e..7391e62516 100644 --- a/studio/backend/core/inference/llama_server_args.py +++ b/studio/backend/core/inference/llama_server_args.py @@ -16,11 +16,18 @@ from __future__ import annotations import os from typing import Iterable, Mapping, Optional +# Valid llama-server --parallel range, shared with LoadRequest.n_parallel. +# Mirrored by callers that cannot import this: run.py and unsloth_cli/commands/ +# studio.py (_PARALLEL_MIN/MAX), per-model-config.ts (N_PARALLEL_MIN/MAX); +# test_parallel_slots_per_load.py pins them together. +PARALLEL_MIN = 1 +PARALLEL_MAX = 64 + # Each group = every alias (short + long) of one hard-denied flag. # Extend the matching group when llama.cpp adds a new alias. _DENYLIST_GROUPS: tuple[frozenset[str], ...] = ( - # Parallel slots: owned by typer --parallel; a pass-through would desync - # app.state.llama_parallel_slots from llama-server. + # Parallel slots: owned by typer --parallel and LoadRequest.n_parallel; a + # pass-through would desync the slot bookkeeping from llama-server. frozenset({"-np", "--parallel", "--n-parallel"}), # Model identity: Unsloth resolves it from LoadRequest; a second -m would # load a different model than Unsloth thinks it loaded. diff --git a/studio/backend/core/inference/mcp_client.py b/studio/backend/core/inference/mcp_client.py index 0256df944e..98112c6d5b 100644 --- a/studio/backend/core/inference/mcp_client.py +++ b/studio/backend/core/inference/mcp_client.py @@ -971,7 +971,12 @@ def _call_stdio_tool( raise RuntimeError("MCP server connection is not available") else: rem = _remaining() - coro = _race_tool_call(session.client.call_tool(name, args), rem, cancel_event) + # raise_on_error=False for the same reason as the one-shot path. + coro = _race_tool_call( + session.client.call_tool(name, args, raise_on_error = False), + rem, + cancel_event, + ) return session.run(coro, rem) except (_MCPCancelled, asyncio.TimeoutError): # _race_tool_call cancels the pending call but cancellation is diff --git a/studio/backend/core/inference/safetensors_agentic.py b/studio/backend/core/inference/safetensors_agentic.py index b593bc119b..3057f7c2ac 100644 --- a/studio/backend/core/inference/safetensors_agentic.py +++ b/studio/backend/core/inference/safetensors_agentic.py @@ -35,6 +35,7 @@ from core.inference.tool_call_parser import ( _strip_mistral_reasoning, BUDGET_EXHAUSTED_NUDGE, MAX_ACT_REPROMPTS, + NUDGE_TOOL_CALLS_STATUS, RAG_MAX_SEARCHES_PER_TURN, RAG_SEARCH_CAP_NUDGE, TOOL_XML_SIGNALS, @@ -1032,9 +1033,10 @@ def run_safetensors_tool_loop( "content": reprompt_to_act_message(tool_hint), } ) - # Empty status clears the badge and resets the route's - # per-turn text cursor before the re-prompted turn streams. + # Blank first: it clears the badge and resets the route's per-turn + # text cursor. The badge then shows the pause is a re-prompt, not a stall. yield {"type": "status", "text": ""} + yield {"type": "status", "text": NUDGE_TOOL_CALLS_STATUS} continue # Final answer. If a literal tool marker in prose was buffered but diff --git a/studio/backend/core/inference/tool_call_parser.py b/studio/backend/core/inference/tool_call_parser.py index 9b6b0a7773..4c3fe234ae 100644 --- a/studio/backend/core/inference/tool_call_parser.py +++ b/studio/backend/core/inference/tool_call_parser.py @@ -183,6 +183,9 @@ INTENT_SIGNAL = re.compile( # times since #5620); safetensors and MLX inherit the same cap from here. MAX_ACT_REPROMPTS = 3 REPROMPT_MAX_CHARS = 2000 +# Composer badge while a hidden re-prompted turn regenerates, else the UI looks +# hung. Matched exactly by the frontend (utils/tool-status.ts); keep in sync. +NUDGE_TOOL_CALLS_STATUS = "Nudging tool calls" def is_short_intent_without_action(text: str) -> bool: diff --git a/studio/backend/models/inference.py b/studio/backend/models/inference.py index acd60dd0b9..0edd1aa37f 100644 --- a/studio/backend/models/inference.py +++ b/studio/backend/models/inference.py @@ -18,6 +18,7 @@ from pydantic import ( model_validator, ) +from core.inference.llama_server_args import PARALLEL_MAX, PARALLEL_MIN from picker.schemas import MAX_CHAT_TEMPLATE_BYTES @@ -113,6 +114,18 @@ class LoadRequest(BaseModel): "'mtp' or 'mtp+ngram'." ), ) + n_parallel: Optional[int] = Field( + None, + ge = PARALLEL_MIN, + le = PARALLEL_MAX, + description = ( + "Parallel decode slots for llama-server (--parallel) for this " + f"load ({PARALLEL_MIN}..{PARALLEL_MAX}). Omit for the server-wide " + "default set at launch (the --parallel CLI flag). The VRAM fitter " + "may launch fewer slots to keep the model fully on GPU. Ignored " + "for non-GGUF models." + ), + ) tensor_parallel: bool = Field( False, description = ( @@ -265,6 +278,16 @@ class ValidateModelRequest(BaseModel): "delegate fitting to llama.cpp, while explicit layers are user-owned." ), ) + n_parallel: Optional[int] = Field( + None, + ge = PARALLEL_MIN, + le = PARALLEL_MAX, + description = ( + "Parallel decode slots intended for the follow-up load, so the " + "coexistence estimate sizes the KV cache like /load. Omit for the " + "server-wide --parallel default." + ), + ) include_context_length: bool = Field( False, description = "Also read the native context length from the local GGUF header. " @@ -533,6 +556,23 @@ class LoadResponse(BaseModel): "or None for automatic selection." ), ) + requested_parallel_slots: Optional[int] = Field( + None, + description = ( + "Parallel decode slots the load was invoked with (per-load " + "n_parallel, else the server-wide --parallel default). None for " + "non-GGUF loads and for the diffusion runner, which ignores " + "--parallel." + ), + ) + parallel_slots: Optional[int] = Field( + None, + description = ( + "Serving slots the active llama-server actually runs (--parallel " + "after any fit-time slot reduction). None for non-GGUF loads and " + "for the diffusion runner, which ignores --parallel." + ), + ) class UnloadResponse(BaseModel): @@ -708,6 +748,23 @@ class InferenceStatusResponse(BaseModel): "or None for automatic selection." ), ) + requested_parallel_slots: Optional[int] = Field( + None, + description = ( + "Parallel decode slots the active load was invoked with (per-load " + "n_parallel, else the server-wide --parallel default). None when " + "no GGUF model is loaded and for the diffusion runner, which " + "ignores --parallel." + ), + ) + parallel_slots: Optional[int] = Field( + None, + description = ( + "Serving slots the active llama-server actually runs (--parallel " + "after any fit-time slot reduction). None when no GGUF model is " + "loaded and for the diffusion runner, which ignores --parallel." + ), + ) llama_cpp_supports_mtp: bool = Field( True, description = ( diff --git a/studio/backend/requirements/extras-no-deps.txt b/studio/backend/requirements/extras-no-deps.txt index 3361af50dd..29d53ba204 100644 --- a/studio/backend/requirements/extras-no-deps.txt +++ b/studio/backend/requirements/extras-no-deps.txt @@ -15,7 +15,9 @@ trl==0.23.1 torch-c-dlpack-ext sentence_transformers==5.2.0 transformers==4.57.6 -pytorch_tokenizers +# No macOS x86_64 wheel at any version, so uv falls back to an sdist that shells out to +# cmake. Skipping it on Intel Macs keeps that install compiler-free. +pytorch_tokenizers; sys_platform != "darwin" or platform_machine == "arm64" kernels==0.12.1 # kernels<3.11 imports tomli as its tomllib fallback; --no-deps skips its own # marker dep, so list it here (no-op on the 3.12/3.13 default installs). diff --git a/studio/backend/requirements/single-env/constraints.txt b/studio/backend/requirements/single-env/constraints.txt index 0a5619924a..7d3b9a081f 100644 --- a/studio/backend/requirements/single-env/constraints.txt +++ b/studio/backend/requirements/single-env/constraints.txt @@ -21,3 +21,20 @@ websockets>=15.0.1 anyio<4.14.0 pandas==2.3.3 + +# av (PyAV) 16+ builds its macOS arm64 wheels against macosx_14_0, so on macOS 13 none +# are installable and the resolver falls back to a source build, which needs FFmpeg +# headers the Xcode CLT do not supply and so fails however that Mac is equipped. +# 15.1.0 is the newest release with a macosx_13_0 arm64 wheel; 17+ moves to cp311-abi3 +# at macosx_14_0 too. +# +# The remaining sdist-only macOS defaults are pure Python, hence allowlisted in +# .github/scripts/clean-machine-assert.sh instead; cryptography below is the one +# other package that would compile. +av<16 + +# cryptography 49.0.0 dropped the macosx_10_9_universal2 wheel for arm64-only, so +# x86_64 macOS has no wheel and builds the sdist, needing Rust plus a working +# linker. 48.0.1 is the newest release with a universal2 wheel. Lift when +# cryptography ships an x86_64-capable macOS wheel again. +cryptography<49; sys_platform == "darwin" and platform_machine == "x86_64" diff --git a/studio/backend/routes/chat_history.py b/studio/backend/routes/chat_history.py index aa59716315..4180518837 100644 --- a/studio/backend/routes/chat_history.py +++ b/studio/backend/routes/chat_history.py @@ -11,6 +11,7 @@ from fastapi import APIRouter, Depends, HTTPException, Query, Request from pydantic import BaseModel, ConfigDict, Field, ValidationError from auth.authentication import get_current_subject +from core.inference.llama_server_args import PARALLEL_MAX, PARALLEL_MIN from loggers import get_logger from utils.utils import safe_curated_detail, log_and_http_error from storage.studio_db import ( @@ -169,6 +170,7 @@ class ChatPresetLoadConfig(BaseModel): kvCacheDtype: Optional[str] = None speculativeType: Optional[str] = None specDraftNMax: Optional[int] = Field(default = None, ge = 1, le = 16) + nParallel: Optional[int] = Field(default = None, ge = PARALLEL_MIN, le = PARALLEL_MAX) tensorParallel: Optional[bool] = None gpuMemoryMode: Optional[Literal["manual"]] = None gpuLayers: Optional[int] = None diff --git a/studio/backend/routes/inference.py b/studio/backend/routes/inference.py index 8b15779a50..d0a2d97f74 100644 --- a/studio/backend/routes/inference.py +++ b/studio/backend/routes/inference.py @@ -727,6 +727,7 @@ def _wants_stream_usage(payload) -> bool: _OPENAI_PASSTHROUGH_TERMINAL_GRACE_S = 2.0 _SSE_DONE_LINE = "data: [DONE]" +_SSE_DONE_CHUNK = "data: [DONE]\n\n" def _openai_passthrough_sse_line_terminal_state(raw_line: str) -> Optional[str]: @@ -2440,10 +2441,16 @@ async def _await_cancel_or_disconnect_then_close_client( return -async def _stop_local_disconnect_cancel_watcher(watcher) -> None: +async def _stop_local_disconnect_cancel_watcher(watcher, timeout_s: float = 5.0) -> None: + # Bounded: this runs in the stream's finally, so awaiting the watcher outright would let a + # wedged poll loop hold the response open forever. asyncio.wait neither cancels nor re-raises, + # and an abandoned watcher owns no resources. watcher.cancel() + done, _pending = await asyncio.wait({watcher}, timeout = timeout_s) + if not done: + return try: - await watcher + watcher.result() except (asyncio.CancelledError, Exception): pass @@ -3294,10 +3301,25 @@ def _is_explicit_tensor_drop(request: LoadRequest) -> bool: return override is not None and override.strip().lower() != "tensor" +def _parallel_slot_echo(llama_backend: LlamaCppBackend) -> dict: + """requested/effective parallel-slot fields for /load and /status echoes. + + The diffusion runner ignores ``--parallel`` and never commits a count, so it + reports None like the non-GGUF paths; echoing the reset placeholder 1 would + fabricate an "invoked with 1 slot".""" + if llama_backend.is_diffusion: + return {"requested_parallel_slots": None, "parallel_slots": None} + return { + "requested_parallel_slots": llama_backend.requested_parallel_slots, + "parallel_slots": llama_backend.effective_parallel_slots, + } + + def _request_matches_loaded_settings( request: LoadRequest, llama_backend: LlamaCppBackend, effective_chat_template_override: Optional[str] = None, + requested_parallel_slots: Optional[int] = None, ) -> bool: """True iff every runtime setting on the request matches the loaded server. Caller has already checked model+variant+is_loaded. See #5401. @@ -3306,11 +3328,22 @@ def _request_matches_loaded_settings( launched (user override, else a bundled family template such as the gemma-4 override), so the dedup compares against what the backend actually holds rather than the raw request field. Defaults to the request field for - callers that do not resolve a bundled override.""" + callers that do not resolve a bundled override. + + ``requested_parallel_slots`` is the resolved count the load would use + (per-load ``n_parallel``, else the server-wide default); None skips it.""" # Compare requested n_ctx (not effective) so VRAM-cap doesn't mask an # Auto-vs-explicit slider flip. if request.max_seq_length != llama_backend.requested_n_ctx: return False + # Requested-vs-requested for the same reason: the fitter may launch fewer + # slots. Diffusion ignores --parallel, so a change there must not reload. + if ( + requested_parallel_slots is not None + and not llama_backend.is_diffusion + and int(requested_parallel_slots) != llama_backend.requested_parallel_slots + ): + return False if _normalise_settings_str(request.cache_type_kv) != _normalise_settings_str( llama_backend.cache_type_kv ): @@ -4730,6 +4763,20 @@ def _guard_chat_load_against_training( cpu_only = LlamaCppBackend._effective_gpu_count() == 0, ) + # Size with the count that will actually launch, or a load that fits gets a + # 409: diffusion never receives --parallel, and load_model clamps to 1 on an + # llama-server without --kv-unified. An unclassified GGUF keeps the ask. + if is_gguf and n_parallel > 1: + if diffusion_kind is True: + n_parallel = 1 + else: + try: + caps = LlamaCppBackend.probe_server_capabilities() + if caps.get("found") and not caps.get("supports_kv_unified"): + n_parallel = 1 + except Exception as e: + logger.warning("Could not probe llama-server slots for chat-load guard: %s", e) + required_override_gb = ( _estimate_gguf_required_gb( config, @@ -5272,6 +5319,17 @@ async def _load_model_impl( backend = get_inference_backend() llama_backend = get_llama_cpp_backend() + # Resolve the slot count once (per-load field, else the server-wide + # --parallel default) so the dedupe, the training guard and the load + # kwargs all size against what launches. app.state stays the launch + # intent / admission fallback; getattr because direct callers have no app. + _app_state = getattr(getattr(fastapi_request, "app", None), "state", None) + _n_parallel = ( + request.n_parallel + if request.n_parallel is not None + else getattr(_app_state, "llama_parallel_slots", 1) + ) + is_direct_gguf_request = model_identifier.lower().endswith(".gguf") if request.gguf_variant or is_direct_gguf_request: gguf_variant_matches = is_direct_gguf_request or bool( @@ -5289,6 +5347,7 @@ async def _load_model_impl( request, llama_backend, effective_chat_template_override, + requested_parallel_slots = _n_parallel, ) # Skip if a prior audio probe failed -- let load_model retry. and getattr(llama_backend, "_audio_probed", True) @@ -5343,6 +5402,7 @@ async def _load_model_impl( n_moe_layers = llama_backend.n_moe_layers, gpu_ids = llama_backend.gpu_ids, requested_gpu_ids = llama_backend.requested_gpu_ids, + **_parallel_slot_echo(llama_backend), ) else: if ( @@ -5481,7 +5541,7 @@ async def _load_model_impl( max_seq_length = request.max_seq_length, requested_gpu_ids = effective_gpu_ids, llama_extra_args = extra_llama_args, - n_parallel = getattr(fastapi_request.app.state, "llama_parallel_slots", 1), + n_parallel = _n_parallel, cache_type_kv = request.cache_type_kv, tensor_parallel = bool(request.tensor_parallel), gpu_memory_mode = request.gpu_memory_mode, @@ -5558,7 +5618,6 @@ async def _load_model_impl( # Route to HF or local mode based on config. Run in a thread so the # event loop stays free for progress polling and other requests # during the (potentially long) GGUF download + llama-server start. - _n_parallel = getattr(fastapi_request.app.state, "llama_parallel_slots", 1) # Load kwargs common to HF and local modes; the two differ only by # the model-source args (hf_repo/-token vs gguf_path/mmproj). @@ -5756,6 +5815,7 @@ async def _load_model_impl( n_moe_layers = llama_backend.n_moe_layers, gpu_ids = llama_backend.gpu_ids, requested_gpu_ids = llama_backend.requested_gpu_ids, + **_parallel_slot_echo(llama_backend), ) # ── Standard path: load via Unsloth/transformers ────────── @@ -6156,9 +6216,14 @@ async def validate_model( requested_gpu_ids = effective_gpu_ids, llama_extra_args = effective_extra_args, n_parallel = ( - getattr(fastapi_request.app.state, "llama_parallel_slots", 1) - if fastapi_request is not None - else 1 + request.n_parallel + if request.n_parallel is not None + # Same getattr chain as the load path: preflight must size like the load. + else getattr( + getattr(getattr(fastapi_request, "app", None), "state", None), + "llama_parallel_slots", + 1, + ) ), cache_type_kv = request.cache_type_kv, tensor_parallel = request.tensor_parallel, @@ -6987,6 +7052,7 @@ async def get_status(current_subject: str = Depends(get_current_subject)): n_moe_layers = llama_backend.n_moe_layers, gpu_ids = llama_backend.gpu_ids, requested_gpu_ids = llama_backend.requested_gpu_ids, + **_parallel_slot_echo(llama_backend), llama_cpp_supports_mtp = _supports_mtp, spec_fallback_reason = llama_backend.spec_fallback_reason, llama_cpp_prebuilt_stale = _stale, @@ -9390,12 +9456,15 @@ async def openai_chat_completions( raise _openai_admission_http_exception(exc, status_code = 429) _tool_sentinel = object() + # True only once the sync generator returned on its own; see _gguf_decode_finished. + _tool_decode_finished = False _cancel_keys = (payload.cancel_id, payload.session_id, completion_id) _tracker = _TrackedCancel.for_payload(cancel_event, payload, *_cancel_keys) _tracker.__enter__() async def gguf_tool_stream(): + nonlocal _tool_decode_finished gen = None next_task = None stream_completed = False @@ -9413,7 +9482,10 @@ async def openai_chat_completions( if lease is None: return if on: - lease.park() + # Refused when the budget is spent: the slot stays here, + # so there is nothing to take back afterwards. + if not lease.park(): + return elif wait: # Resuming: park() may have handed our slot to a waiter, so wait for room instead # of putting two holders on one slot. @@ -9480,6 +9552,7 @@ async def openai_chat_completions( if next_task.done(): next_task = None if event is _tool_sentinel: + _tool_decode_finished = True break # Anything after the gated tool_start means the user answered. @@ -9696,6 +9769,13 @@ async def openai_chat_completions( stream_started = True try: async for chunk in iterator: + # Release before the yield; see gguf_stream_chunks. + if ( + lease is not None + and _tool_decode_finished + and chunk == _SSE_DONE_CHUNK + ): + lease.release() yield chunk except asyncio.CancelledError: stream_cancelled = True @@ -9998,6 +10078,9 @@ async def openai_chat_completions( ) _gguf_sentinel = object() + # True only once the sync generator returned on its own: only then has _open_stream's + # client exited. A cancel still emits [DONE] without it. + _gguf_decode_finished = False if payload.stream: if _wants_multiple_choices(payload): @@ -10024,6 +10107,7 @@ async def openai_chat_completions( raise _openai_admission_http_exception(exc, status_code = 429) async def gguf_stream_chunks(): + nonlocal _gguf_decode_finished disconnect_watcher = asyncio.create_task( _await_disconnect_then_cancel(request, cancel_event) ) @@ -10068,6 +10152,7 @@ async def openai_chat_completions( if next_task.done(): next_task = None if cumulative is _gguf_sentinel: + _gguf_decode_finished = True break # Capture server metadata for the final usage chunk if isinstance(cumulative, dict): @@ -10230,6 +10315,20 @@ async def openai_chat_completions( stream_started = True try: async for chunk in iterator: + # The slot is idle once the sync generator returned and the stream ends + # with the plain sentinel. The finally only runs at ASGI teardown, so + # waiting for it starves the next request. Release before the yield: a + # stalled send() or a consumer that stops pulling parks us there, and + # Starlette never aclose()s a body iterator. Release is idempotent, so + # the finally stays the backstop. Exact equality, not endswith: + # _openai_stream_error_sse ends in the same sentinel before its + # cleanup runs, and that stream still owns the slot. + if ( + lease is not None + and _gguf_decode_finished + and chunk == _SSE_DONE_CHUNK + ): + lease.release() yield chunk except asyncio.CancelledError: stream_cancelled = True diff --git a/studio/backend/run.py b/studio/backend/run.py index e18c49e01a..c4824ab417 100644 --- a/studio/backend/run.py +++ b/studio/backend/run.py @@ -2130,7 +2130,8 @@ def _build_arg_parser(): default = _PARALLEL_DEFAULT_PLAIN, help = ( f"llama-server parallel decode slots ({_PARALLEL_MIN}..{_PARALLEL_MAX}). " - f"Default {_PARALLEL_DEFAULT_PLAIN}." + f"Default {_PARALLEL_DEFAULT_PLAIN}. The Studio run settings " + "(Parallel Slots) override it per load." ), ) return parser diff --git a/studio/backend/tests/test_gguf_stream_slot_release.py b/studio/backend/tests/test_gguf_stream_slot_release.py new file mode 100644 index 0000000000..4390f364c8 --- /dev/null +++ b/studio/backend/tests/test_gguf_stream_slot_release.py @@ -0,0 +1,267 @@ +# SPDX-License-Identifier: AGPL-3.0-only +# Copyright 2026-present the Unsloth AI Inc. team. All rights reserved. + +"""A finished GGUF chat stream must free its llama-server slot at [DONE]. + +llama-server has a fixed slot count, gated by an admission lease. Releasing that lease only in +the stream's outer finally, which runs at ASGI teardown, let a wedged teardown pin a slot +llama-server had already freed, so the next chat request queued behind a finished generation +with no timeout to bound the wait. + +The wedge below stands in for the real one: the frontend never cancels its reader after [DONE] +(chat-api.ts), and uvicorn advertises ASGI spec_version 2.3, so Starlette's +OSError/ClientDisconnect path, the only disconnect detector _SameTaskStreamingResponse keeps, +cannot fire. +""" + +import asyncio +import json + +import pytest +from fastapi import FastAPI + +from auth.authentication import get_current_subject +from core.inference import llama_admission +import routes.inference as inference_route + + +@pytest.fixture(autouse = True) +def _fresh_queues(): + llama_admission.reset_llama_admission_queues() + yield + llama_admission.reset_llama_admission_queues() + + +def _active_slots() -> int: + with llama_admission._QUEUES_LOCK: + queues = list(llama_admission._QUEUES.values()) + return sum(queue.snapshot().active for queue in queues) + + +_ONE_SLOT = llama_admission.LlamaAdmissionConfig(max_queue = 4) + + +def _reserve_one_slot(): + """Take the single slot of a 1-parallel backend. Needs a running loop.""" + queue = llama_admission.get_llama_admission_queue("http://llama.test") + reservation = queue.reserve(capacity = 1, config = _ONE_SLOT) + return queue, reservation.lease_nowait() + + +def test_slot_is_freed_at_done_even_if_teardown_never_finishes(): + """Yield chunks, then wedge in the finally: without the release at [DONE] the slot stays + held for as long as the teardown is stuck, which is what starved the next request in CI. + """ + wedged = asyncio.Event() + + async def _stream(): + try: + yield 'data: {"choices": [{"delta": {"content": "hi"}}]}\n\n' + yield "data: [DONE]\n\n" + finally: + # Stand-in for a teardown that never completes. + await wedged.wait() + + async def _admitted(held): + iterator = _stream() + try: + async for chunk in iterator: + yield chunk + if held is not None and chunk == inference_route._SSE_DONE_CHUNK: + held.release() + finally: + if held is not None: + held.release() + + async def _drive(): + queue, lease = _reserve_one_slot() + assert lease is not None + assert _active_slots() == 1 + + seen = [] + saw_done = asyncio.Event() + + async def _consume(): + # Like Starlette's stream_response: it keeps pulling after the last chunk, so the + # generator resumes past [DONE] and only then runs into the wedged teardown. + async for chunk in _admitted(lease): + seen.append(chunk) + if chunk == inference_route._SSE_DONE_CHUNK: + saw_done.set() + + task = asyncio.create_task(_consume()) + try: + await asyncio.wait_for(saw_done.wait(), timeout = 5.0) + # Give the generator a turn to resume past the [DONE] yield and reach the wedge. + for _ in range(50): + if _active_slots() == 0: + break + await asyncio.sleep(0.01) + assert not task.done(), "teardown should still be wedged" + assert _active_slots() == 0, ( + "slot still held after [DONE]; the next chat request would " + "queue behind a generation that already finished" + ) + # A second caller must be admitted right away. + second = queue.reserve(capacity = 1, config = _ONE_SLOT).lease_nowait() + assert second is not None, "next request was refused a free slot" + second.release() + finally: + wedged.set() + task.cancel() + await asyncio.gather(task, return_exceptions = True) + return seen + + seen = asyncio.run(_drive()) + assert seen[-1] == "data: [DONE]\n\n" + + +def test_release_is_idempotent_so_the_finally_stays_a_backstop(): + async def _drive(): + _queue, lease = _reserve_one_slot() + assert _active_slots() == 1 + lease.release() + lease.release() + assert _active_slots() == 0 + + asyncio.run(_drive()) + + +def test_stopping_the_disconnect_watcher_cannot_hang(): + """The watcher stop runs in the stream's finally; it must be bounded.""" + + async def _drive(): + started = asyncio.Event() + + release = asyncio.Event() + + async def _unstoppable(): + started.set() + while not release.is_set(): + try: + await asyncio.sleep(0.01) + except asyncio.CancelledError: + # Swallow cancellation, as the real watcher does on its way out. + if release.is_set(): + raise + continue + + watcher = asyncio.create_task(_unstoppable()) + await started.wait() + # Would hang forever if the stop awaited the watcher outright. + await asyncio.wait_for( + inference_route._stop_local_disconnect_cancel_watcher(watcher, timeout_s = 0.2), + timeout = 5.0, + ) + assert not watcher.done(), "watcher should have been abandoned, not awaited" + release.set() + watcher.cancel() + await asyncio.gather(watcher, return_exceptions = True) + + asyncio.run(_drive()) + + +class _OneSlotGgufBackend: + """A loaded 1-parallel GGUF backend, the shape CI runs.""" + + is_loaded = True + model_identifier = "test/model.gguf" + base_url = "http://llama.test" + effective_parallel_slots = 1 + _is_audio = False + is_vision = False + supports_tools = False + + def generate_chat_completion(self, **kwargs): + yield "hi" + yield { + "type": "metadata", + "usage": {"prompt_tokens": 3, "completion_tokens": 1, "total_tokens": 4}, + "timings": {"prompt_n": 3, "predicted_n": 1}, + "finish_reason": "stop", + } + + +def test_real_stream_frees_the_slot_at_done_with_a_wedged_teardown(monkeypatch): + """Drive the real ASGI route, wedged exactly where CI wedged. + + Hanging ``_stop_local_disconnect_cancel_watcher``, which runs in ``gguf_stream_chunks``'s + success-path finally, leaves a response that has sent [DONE] but cannot finish. + """ + monkeypatch.setattr(inference_route, "get_llama_cpp_backend", lambda: _OneSlotGgufBackend()) + monkeypatch.setattr(inference_route, "_effective_enable_tools", lambda payload: False) + + app = FastAPI() + app.include_router(inference_route.router) + app.dependency_overrides[get_current_subject] = lambda: "test-user" + + async def _drive(): + wedged = asyncio.Event() + + async def _hang(watcher, *args, **kwargs): + watcher.cancel() + await wedged.wait() + + monkeypatch.setattr(inference_route, "_stop_local_disconnect_cancel_watcher", _hang) + + body = json.dumps( + {"messages": [{"role": "user", "content": "hi"}], "stream": True} + ).encode() + scope = { + "type": "http", + "asgi": {"version": "3.0", "spec_version": "2.3"}, + "http_version": "1.1", + "method": "POST", + "scheme": "http", + "path": "/chat/completions", + "raw_path": b"/chat/completions", + "query_string": b"", + "root_path": "", + "headers": [ + (b"host", b"testserver"), + (b"content-type", b"application/json"), + (b"content-length", str(len(body)).encode()), + ], + "client": ("127.0.0.1", 12345), + "server": ("testserver", 80), + "app": app, + } + + sent_body = asyncio.Event() + frames = [] + + async def receive(): + if not frames: + return {"type": "http.request", "body": body, "more_body": False} + # Never disconnect: the browser keeps the socket open after [DONE]. + await asyncio.Event().wait() + + async def send(message): + frames.append(message) + if message.get("type") == "http.response.body": + chunk = message.get("body", b"").decode() + if chunk == inference_route._SSE_DONE_CHUNK: + sent_body.set() + + task = asyncio.create_task(app(scope, receive, send)) + try: + await asyncio.wait_for(sent_body.wait(), timeout = 20.0) + for _ in range(200): + if _active_slots() == 0: + break + await asyncio.sleep(0.01) + assert not task.done(), "response should still be wedged in teardown" + assert _active_slots() == 0, ( + "slot still held after [DONE] on the real route; the next chat " + "request would queue behind a finished generation" + ) + queue = llama_admission.get_llama_admission_queue("http://llama.test") + second = queue.reserve(capacity = 1, config = _ONE_SLOT).lease_nowait() + assert second is not None, "next request was refused a free slot" + second.release() + finally: + wedged.set() + task.cancel() + await asyncio.gather(task, return_exceptions = True) + + asyncio.run(_drive()) diff --git a/studio/backend/tests/test_gguf_stream_slot_release_ordering.py b/studio/backend/tests/test_gguf_stream_slot_release_ordering.py new file mode 100644 index 0000000000..7a8ceb4f53 --- /dev/null +++ b/studio/backend/tests/test_gguf_stream_slot_release_ordering.py @@ -0,0 +1,316 @@ +# SPDX-License-Identifier: AGPL-3.0-only +# Copyright 2026-present the Unsloth AI Inc. team. All rights reserved. + +"""Ordering rules for the early admission release at ``data: [DONE]``. + +Freeing the llama-server slot at the sentinel is only correct when two things hold, and on a +one-slot backend both are load-bearing: + +1. The release happens *before* the sentinel reaches the ASGI ``send()``. Starlette's + ``stream_response`` suspends the body iterator at its ``yield`` for the whole of + ``await send(...)``, and uvicorn's ``send()`` awaits ``flow.drain()`` on a write-paused + transport, so a client that stops reading parks the generator there indefinitely. Starlette + never ``aclose()``s a body iterator either, so that generator's ``finally`` is left to GC. + +2. The sentinel really means "llama-server is done with this request". Two other emitters end + in the same bytes: ``_openai_stream_error_sse``, yielded from inside the still-suspended + generator's ``except`` block, and the cancel path, which breaks the read loop while the sync + generator is still parked on a yield inside ``_open_stream``'s httpx client. +""" + +import asyncio +import json +import threading + +import pytest +from fastapi import FastAPI + +from auth.authentication import get_current_subject +from core.inference import llama_admission +import routes.inference as inference_route + + +@pytest.fixture(autouse = True) +def _fresh_queues(): + llama_admission.reset_llama_admission_queues() + yield + llama_admission.reset_llama_admission_queues() + + +def _active_slots() -> int: + with llama_admission._QUEUES_LOCK: + queues = list(llama_admission._QUEUES.values()) + return sum(queue.snapshot().active for queue in queues) + + +class _OneSlotBackend: + """A loaded 1-parallel GGUF backend, the shape CI runs.""" + + is_loaded = True + model_identifier = "test/model.gguf" + base_url = "http://llama.test" + effective_parallel_slots = 1 + _is_audio = False + is_vision = False + supports_tools = False + + def __init__(self): + self.closing = threading.Event() + self.finish_close = threading.Event() + self.closed = threading.Event() + self.cancel_event = None + + def generate_chat_completion(self, **kwargs): + raise NotImplementedError + + +class _CompletingBackend(_OneSlotBackend): + def generate_chat_completion(self, **kwargs): + yield "hi" + yield { + "type": "metadata", + "usage": {"prompt_tokens": 3, "completion_tokens": 1, "total_tokens": 4}, + "timings": {"prompt_n": 3, "predicted_n": 1}, + "finish_reason": "stop", + } + + +class _FailsMidStreamBackend(_OneSlotBackend): + """Still decoding when the route's own chunk handling blows up. + + ``gen`` stays parked on its ``yield`` until the stream's ``finally`` closes it, and only + that close drops the httpx stream llama-server is writing to. + """ + + def generate_chat_completion(self, **kwargs): + try: + yield "a" + yield "ab" + yield "abc" + except GeneratorExit: + self.closing.set() + # Stand in for the time llama-server needs to notice the drop and free its slot. + self.finish_close.wait(10.0) + self.closed.set() + raise + + +class _CancelledMidStreamBackend(_OneSlotBackend): + """Cancelled by the user halfway through, the Stop-button path.""" + + def generate_chat_completion( + self, + cancel_event = None, + **kwargs, + ): + self.cancel_event = cancel_event + try: + yield "a" + cancel_event.set() + yield "ab" + yield "abc" + except GeneratorExit: + self.closed.set() + raise + + +def _scope(app, body: bytes) -> dict: + return { + "type": "http", + "asgi": {"version": "3.0", "spec_version": "2.3"}, + "http_version": "1.1", + "method": "POST", + "scheme": "http", + "path": "/chat/completions", + "raw_path": b"/chat/completions", + "query_string": b"", + "root_path": "", + "headers": [ + (b"host", b"testserver"), + (b"content-type", b"application/json"), + (b"content-length", str(len(body)).encode()), + ], + "client": ("127.0.0.1", 12345), + "server": ("testserver", 80), + "app": app, + } + + +def _build_app(monkeypatch, backend): + monkeypatch.setattr(inference_route, "get_llama_cpp_backend", lambda: backend) + monkeypatch.setattr(inference_route, "_effective_enable_tools", lambda payload: False) + app = FastAPI() + app.include_router(inference_route.router) + app.dependency_overrides[get_current_subject] = lambda: "test-user" + return app + + +def _request_body() -> bytes: + return json.dumps({"messages": [{"role": "user", "content": "hi"}], "stream": True}).encode() + + +def test_slot_is_free_before_the_done_frame_reaches_send(monkeypatch): + """The release must not sit behind ``await send(...)``. + + uvicorn's ``send()`` awaits ``flow.drain()`` on a write-paused socket (h11_impl.py), so a + client that stops reading parks the body iterator on its ``yield`` indefinitely. Anything + after that ``yield`` is unreachable, and Starlette never ``aclose()``s the iterator, so the + outer ``finally`` is left to GC. + """ + backend = _CompletingBackend() + app = _build_app(monkeypatch, backend) + + async def _drive(): + body = _request_body() + frames = [] + slots_at_done = [] + finished = asyncio.Event() + + async def receive(): + if not frames: + return {"type": "http.request", "body": body, "more_body": False} + await asyncio.Event().wait() + + async def send(message): + frames.append(message) + if message.get("type") != "http.response.body": + return + if message.get("body", b"").decode() == "data: [DONE]\n\n": + # Sampled exactly where a stalled client would wedge. + slots_at_done.append(_active_slots()) + finished.set() + + task = asyncio.create_task(app(_scope(app, body), receive, send)) + try: + await asyncio.wait_for(finished.wait(), timeout = 20.0) + finally: + task.cancel() + await asyncio.gather(task, return_exceptions = True) + + assert slots_at_done == [0], ( + "the slot was still held while the [DONE] frame was being written; " + "a client that stops reading would pin it there indefinitely" + ) + + asyncio.run(_drive()) + + +def test_error_sentinel_keeps_the_slot_until_the_generator_is_closed(monkeypatch): + """``_openai_stream_error_sse`` ends in ``data: [DONE]`` but is not a finish. + + It is yielded from inside ``gguf_stream_chunks``'s ``except`` block, so the generator has + not yet run its ``finally``: the worker is undrained and ``gen`` is still open with + llama-server streaming into it. Freeing the slot there puts two callers on a one-slot + backend. + """ + backend = _FailsMidStreamBackend() + app = _build_app(monkeypatch, backend) + + calls = {"n": 0} + + def _boom(monitor_id, text): + calls["n"] += 1 + if calls["n"] >= 2: + raise RuntimeError("chunk handling failed") + + monkeypatch.setattr(inference_route.api_monitor, "append_reply", _boom) + + async def _drive(): + body = _request_body() + frames = [] + saw_error = asyncio.Event() + + async def receive(): + if not frames: + return {"type": "http.request", "body": body, "more_body": False} + await asyncio.Event().wait() + + async def send(message): + frames.append(message) + if message.get("type") != "http.response.body": + return + chunk = message.get("body", b"").decode() + # The error form: a payload line plus the sentinel, in one chunk. + if chunk.endswith("data: [DONE]\n\n") and chunk != "data: [DONE]\n\n": + saw_error.set() + + task = asyncio.create_task(app(_scope(app, body), receive, send)) + try: + await asyncio.wait_for(saw_error.wait(), timeout = 20.0) + # Wait until cleanup reaches gen.close(), so llama-server still holds the slot. + for _ in range(500): + if backend.closing.is_set(): + break + await asyncio.sleep(0.01) + assert backend.closing.is_set(), "cleanup never reached gen.close()" + assert _active_slots() == 1, ( + "slot handed out while the failed request still owned " + "llama-server; the next request would exceed the configured " + "parallelism" + ) + finally: + backend.finish_close.set() + task.cancel() + await asyncio.gather(task, return_exceptions = True) + + asyncio.run(_drive()) + + +def test_cancelled_stream_keeps_the_slot_until_the_generator_is_closed(monkeypatch): + """A cancelled stream emits the plain sentinel with ``gen`` still open. + + ``cancel_event.is_set()`` breaks the read loop at the top, so the sync generator never + reaches StopIteration and stays parked on a ``yield`` inside ``_open_stream``'s httpx + client. ``stream_completed`` is set all the same, which also makes the ``finally`` skip + ``gen.close()``, so ``data: [DONE]`` here does not mean llama-server is finished. + """ + backend = _CancelledMidStreamBackend() + app = _build_app(monkeypatch, backend) + + wedged = asyncio.Event() + + async def _hang(watcher, *args, **kwargs): + watcher.cancel() + await wedged.wait() + + monkeypatch.setattr(inference_route, "_stop_local_disconnect_cancel_watcher", _hang) + + async def _drive(): + body = _request_body() + frames = [] + saw_done = asyncio.Event() + + async def receive(): + if not frames: + return {"type": "http.request", "body": body, "more_body": False} + await asyncio.Event().wait() + + async def send(message): + frames.append(message) + if message.get("type") != "http.response.body": + return + if message.get("body", b"").decode() == "data: [DONE]\n\n": + saw_done.set() + + task = asyncio.create_task(app(_scope(app, body), receive, send)) + try: + await asyncio.wait_for(saw_done.wait(), timeout = 20.0) + for _ in range(50): + if _active_slots() == 0: + break + await asyncio.sleep(0.01) + assert backend.cancel_event is not None and backend.cancel_event.is_set() + assert ( + not backend.closed.is_set() + ), "test setup: the generator should still be open here" + assert _active_slots() == 1, ( + "slot freed on a cancelled stream whose llama-server request is " + "still open; the next request would exceed the configured " + "parallelism" + ) + finally: + wedged.set() + task.cancel() + await asyncio.gather(task, return_exceptions = True) + + asyncio.run(_drive()) diff --git a/studio/backend/tests/test_llama_admission.py b/studio/backend/tests/test_llama_admission.py index 9ff19ec27d..1b1aeb1cc5 100644 --- a/studio/backend/tests/test_llama_admission.py +++ b/studio/backend/tests/test_llama_admission.py @@ -1066,3 +1066,229 @@ def test_an_immediate_arrival_cannot_take_an_approved_chats_slot(): assert queue.snapshot().active <= 1 asyncio.run(scenario()) + + +def test_parking_is_bounded_so_the_thread_pool_cannot_be_drained(monkeypatch): + # A pending prompt parks an executor thread (the loop blocks inside + # to_thread(next, gen)) and frees a slot that admits another run which can + # park too, so unbounded parking drains the pool the generators run on. + # Pinned because the real budget follows the runner's usable CPUs. + monkeypatch.setattr(llama_admission, "_executor_workers", lambda: 32) + + async def scenario(): + queue = get_llama_admission_queue("http://llama.test") + config = LlamaAdmissionConfig() + limit = llama_admission._max_parked(1) + assert limit >= 1 + + leases = [] + for _ in range(limit): + lease = queue.reserve(capacity = 1, config = config).lease_nowait() + assert lease is not None and lease.park() + leases.append(lease) + + refused = queue.reserve(capacity = 1, config = config).lease_nowait() + assert refused is not None + assert not refused.park(), "parking is unbounded" + # Refusing means keeping the slot, the old behaviour, not an error. + assert refused.slot is not None + assert queue.snapshot().active == 1 + + leases[0].unpark() + assert refused.park(), "budget was not returned" + for lease in leases[1:] + [refused]: + lease.release() + leases[0].release() + + asyncio.run(scenario()) + + +def test_the_park_budget_is_shared_by_every_queue(monkeypatch): + # One executor, so a per-queue budget would be handed out again to every + # backend and to every reload onto a fresh ephemeral port. + monkeypatch.setattr(llama_admission, "_executor_workers", lambda: 32) + + async def scenario(): + config = LlamaAdmissionConfig() + first = get_llama_admission_queue("http://llama.test:1") + second = get_llama_admission_queue("http://llama.test:2") + limit = llama_admission._max_parked(1) + + for index in range(limit): + queue = first if index % 2 == 0 else second + lease = queue.reserve(capacity = 1, config = config).lease_nowait() + assert lease.park() + + spare = second.reserve(capacity = 1, config = config).lease_nowait() + assert not spare.park(), "each queue got its own budget" + + # A reset drops the queues the count was claimed against, so it must drop + # the count too or the leak shrinks the budget process-wide. + reset_llama_admission_queues() + revived = get_llama_admission_queue("http://llama.test:1") + fresh = revived.reserve(capacity = 1, config = config).lease_nowait() + assert fresh.park(), "reset leaked the park count" + fresh.release() + + asyncio.run(scenario()) + + +def test_the_park_budget_leaves_the_executor_room_to_work(monkeypatch): + # The pool already permits `capacity` pending prompts and every park admits + # one more, so the budget must account for both. Swept across executor sizes + # rather than read off this host, since a container gets a small one. + for cpus in (1, 2, 4, 8, 16, 28, 64): + workers = min(32, cpus + 4) + monkeypatch.setattr(llama_admission, "_executor_workers", lambda w = workers: w) + reserve = llama_admission._executor_reserve(workers) + assert reserve >= 2, f"{workers} workers left no reserve" + + # Even the smallest executor fits the two simultaneous prompts #7455 needs. + assert llama_admission._max_parked(1) >= 2, f"no room for two on {workers} workers" + assert llama_admission._max_parked(1) <= workers // 2 + # A backend whose --parallel alone fills the executor gets no parks. + assert llama_admission._max_parked(workers) == 0 + for capacity in range(0, workers + 8): + budget = llama_admission._max_parked(capacity) + assert budget >= 0, f"negative budget at capacity {capacity}" + assert ( + budget == 0 or capacity + budget <= workers - reserve + ), f"{workers} workers: capacity {capacity} plus {budget} parks leaves no room" + + +def test_the_park_budget_follows_the_executors_own_cpu_count(monkeypatch): + # 3.13 sizes ThreadPoolExecutor from process_cpu_count(), which honours CPU + # affinity and cgroup quotas; cpu_count() would budget from the whole host + # inside a one-core container. Pulled apart here, since they usually match. + import concurrent.futures + + monkeypatch.setattr(os, "cpu_count", lambda: 64) + if hasattr(os, "process_cpu_count"): + monkeypatch.setattr(os, "process_cpu_count", lambda: 1) + # Against the real thing rather than the formula: the default executor is a + # plain ThreadPoolExecutor(), so its own sizing is the answer on any version. + with concurrent.futures.ThreadPoolExecutor() as pool: + assert llama_admission._executor_workers() == pool._max_workers + + +def test_the_stream_retries_a_park_that_was_refused(): + # _park_admission short-circuits on `on == _parked`, so recording a refused + # park as parked would skip every later approval in the run even once the + # budget frees up. Structural because that only shows on a second approval. + import ast + + # Read rather than import: routes.inference pulls in the whole app. + route = os.path.join(_backend, "routes", "inference.py") + with open(route, encoding = "utf-8") as handle: + tree = ast.parse(handle.read()) + helpers = [ + node + for node in ast.walk(tree) + if isinstance(node, ast.AsyncFunctionDef) and node.name == "_park_admission" + ] + assert len(helpers) == 1, f"expected one _park_admission, found {len(helpers)}" + + guards = [ + node + for node in ast.walk(helpers[0]) + if isinstance(node, ast.If) + and isinstance(node.test, ast.UnaryOp) + and isinstance(node.test.op, ast.Not) + and isinstance(node.test.operand, ast.Call) + and getattr(node.test.operand.func, "attr", None) == "park" + and getattr(node.test.operand.func.value, "id", None) == "lease" + ] + assert len(guards) == 1, "lease.park()'s answer is ignored" + assert all( + isinstance(stmt, ast.Return) for stmt in guards[0].body + ), "a refused park must leave _parked alone, so a later approval retries it" + + +def test_the_park_budget_counts_every_live_backend(monkeypatch): + # base_url takes a fresh port on every load, so a reload mints a queue while + # the old one drains. Prompts on both park threads of the one executor, so a + # budget sized from either backend alone lets them add up past the reserve. + monkeypatch.setattr(llama_admission, "_executor_workers", lambda: 32) + + async def scenario(): + config = LlamaAdmissionConfig() + old = get_llama_admission_queue("http://llama.test:1") + draining = old.reserve(capacity = 16, config = config).lease_nowait() + assert draining is not None # in flight, so the registry keeps this queue + + new = get_llama_admission_queue("http://llama.test:2") + lease = new.reserve(capacity = 16, config = config).lease_nowait() + assert lease is not None + + # 16 slots each against 32 workers: their prompts alone can fill it. + assert llama_admission._max_parked(16) > 0, "this test needs a budget to remove" + assert not lease.park(), "budget sized from one backend of two" + + draining.release() # the old backend drains and is up for eviction + assert lease.park(), "an idle backend still counted against the budget" + lease.release() + + asyncio.run(scenario()) + + +def test_the_park_budget_is_freed_when_the_prompt_is_answered(monkeypatch): + # The executor thread comes back the moment the answer arrives, before the + # resume queues for a slot. Holding the budget until the slot lands refuses + # someone else's park, and that someone holds the slot the resumer wants. + monkeypatch.setattr(llama_admission, "_executor_workers", lambda: 32) + + async def scenario(): + config = LlamaAdmissionConfig() + queue = get_llama_admission_queue("http://llama.test") + + parked = [] + for _ in range(llama_admission._max_parked(1)): + lease = queue.reserve(capacity = 1, config = config).lease_nowait() + assert lease is not None and lease.park() + parked.append(lease) + + blocked = queue.reserve(capacity = 1, config = config).lease_nowait() + assert blocked is not None + assert not blocked.park(), "the budget was not full to begin with" + + # One prompt is answered. Its slot is taken, so the resume queues for one. + resumed = asyncio.ensure_future(parked[0].unpark_async(poll_s = 0.01)) + await asyncio.sleep(0.05) + assert not resumed.done(), "the resume needs to still be waiting for its slot" + + assert blocked.park(), "budget held for a prompt wait that is over" + # Which is what frees the slot the resumer was waiting for. + await asyncio.wait_for(resumed, timeout = 2) + for lease in parked[1:] + [blocked]: + lease.release() + parked[0].release() + + asyncio.run(scenario()) + + +def test_releasing_a_parked_holder_returns_its_budget(monkeypatch): + # A client that disconnects on the prompt releases straight out of parked, + # never unparking. Its executor thread went with it, so keeping the budget + # would lose one for the life of the process. + monkeypatch.setattr(llama_admission, "_executor_workers", lambda: 32) + + async def scenario(): + config = LlamaAdmissionConfig() + queue = get_llama_admission_queue("http://llama.test") + + parked = [] + for _ in range(llama_admission._max_parked(1)): + lease = queue.reserve(capacity = 1, config = config).lease_nowait() + assert lease is not None and lease.park() + parked.append(lease) + + blocked = queue.reserve(capacity = 1, config = config).lease_nowait() + assert blocked is not None + assert not blocked.park(), "the budget was not full to begin with" + + parked[0].release() + assert blocked.park(), "a released park never gave its budget back" + for lease in parked[1:] + [blocked]: + lease.release() + + asyncio.run(scenario()) diff --git a/studio/backend/tests/test_llama_cpp_tool_loop.py b/studio/backend/tests/test_llama_cpp_tool_loop.py index c629ff3be4..cbd1b07505 100644 --- a/studio/backend/tests/test_llama_cpp_tool_loop.py +++ b/studio/backend/tests/test_llama_cpp_tool_loop.py @@ -26,6 +26,7 @@ from core.inference.llama_cpp import ( _PROVISIONAL_ARGS_MIN_CHARS, LlamaCppBackend, ) +from core.inference.tool_call_parser import NUDGE_TOOL_CALLS_STATUS from state import tool_approvals from state.tool_approvals import TOOL_REJECTED_MESSAGE, resolve_tool_decision @@ -1841,6 +1842,140 @@ def test_reprompted_tool_call_still_streams_final_answer(monkeypatch): assert len(payloads) == 3 +def _status_texts(events: list[dict]) -> list[str]: + return [event["text"] for event in events if event.get("type") == "status"] + + +_WEB_SEARCH_TOOL = { + "type": "function", + "function": { + "name": "web_search", + "description": "Search the web.", + "parameters": { + "type": "object", + "properties": {"query": {"type": "string"}}, + "required": ["query"], + }, + }, +} + + +def _nudge_then_search_streams() -> list[list[str]]: + """Stall, then a re-prompted turn that finally searches, then the answer.""" + + return [ + [_sse({"content": "I will search the web now."}), _done()], + [ + _sse( + { + "tool_calls": [ + { + "index": 0, + "id": "call_search", + "type": "function", + "function": { + "name": "web_search", + "arguments": json.dumps({"query": "red square"}), + }, + } + ] + } + ), + _done(), + ], + [_sse({"content": "Final answer: the square is red."}), _done()], + ] + + +def test_plan_without_action_nudge_is_announced_on_the_status_channel(monkeypatch): + """The re-prompted turn is hidden, so without a badge the UI looks frozen.""" + + payloads: list[dict] = [] + backend = _make_backend(monkeypatch, _nudge_then_search_streams(), payloads) + monkeypatch.setattr( + "core.inference.tools.execute_tool", + lambda *_a, **_k: "Search results: red is #f00.", + ) + + events = list( + backend.generate_chat_completion_with_tools( + messages = [{"role": "user", "content": "What colour is the square?"}], + tools = [_WEB_SEARCH_TOOL], + max_tool_iterations = 2, + ) + ) + + statuses = _status_texts(events) + assert NUDGE_TOOL_CALLS_STATUS in statuses + index = statuses.index(NUDGE_TOOL_CALLS_STATUS) + # Blank first: the route resets its text cursor only on an empty status. + # index > 0 matters: at 0, statuses[-1] wraps to the terminal clear. + assert index > 0 and statuses[index - 1] == "" + assert statuses[index + 1].startswith("Searching:") + assert statuses[-1] == "" + + +def test_plan_without_action_nudge_status_clears_when_the_retry_just_answers(monkeypatch): + streams = [ + [_sse({"content": "I will search the web now."}), _done()], + [_sse({"content": "No search needed. Final answer: the square is red."}), _done()], + ] + payloads: list[dict] = [] + backend = _make_backend(monkeypatch, streams, payloads) + + events = list( + backend.generate_chat_completion_with_tools( + messages = [{"role": "user", "content": "What colour is the square?"}], + tools = [_WEB_SEARCH_TOOL], + max_tool_iterations = 2, + ) + ) + + statuses = _status_texts(events) + assert NUDGE_TOOL_CALLS_STATUS in statuses + assert statuses[-1] == "" + + +def test_direct_answer_never_shows_the_nudge_status(monkeypatch): + payloads: list[dict] = [] + backend = _make_backend( + monkeypatch, + [[_sse({"content": "The square is red."}), _done()]], + payloads, + ) + + events = list( + backend.generate_chat_completion_with_tools( + messages = [{"role": "user", "content": "What colour is the square?"}], + tools = [_WEB_SEARCH_TOOL], + max_tool_iterations = 2, + ) + ) + + assert NUDGE_TOOL_CALLS_STATUS not in _status_texts(events) + + +def test_nudge_status_absent_when_nudging_is_disabled(monkeypatch): + payloads: list[dict] = [] + backend = _make_backend(monkeypatch, _nudge_then_search_streams(), payloads) + monkeypatch.setattr( + "core.inference.tools.execute_tool", + lambda *_a, **_k: "Search results: red is #f00.", + ) + + events = list( + backend.generate_chat_completion_with_tools( + messages = [{"role": "user", "content": "What colour is the square?"}], + tools = [_WEB_SEARCH_TOOL], + max_tool_iterations = 2, + nudge_tool_calls = False, + ) + ) + + assert NUDGE_TOOL_CALLS_STATUS not in _status_texts(events) + assert len(payloads) == 1 + + def test_confirm_tool_calls_allow_executes_gguf_tool(monkeypatch): streams = [ _structured_tool_call("python", {"code": "print(1)"}, "call_py"), diff --git a/studio/backend/tests/test_llama_server_args.py b/studio/backend/tests/test_llama_server_args.py index b2ec5034ac..83934e4130 100644 --- a/studio/backend/tests/test_llama_server_args.py +++ b/studio/backend/tests/test_llama_server_args.py @@ -77,8 +77,7 @@ validate_extra_args = _lsa.validate_extra_args ["--reasoning-format", "deepseek"], ["-rea", "auto"], # Soft-managed: user flags last-wins over Unsloth's auto-set version. - # --parallel / -np / --n-parallel are hard-denied (KV-cache + slot - # count would desync); use `unsloth studio run --parallel N` instead. + # --parallel / -np / --n-parallel are hard-denied; use Parallel Slots. ["-c", "131072"], ["--ctx-size", "8192"], ["--flash-attn", "off"], @@ -128,7 +127,7 @@ def test_non_flag_token_passes_through(): @pytest.mark.parametrize( "denied", [ - # Parallel slots -- owned by the typer --parallel flag. + # Parallel slots -- owned by typer --parallel and LoadRequest.n_parallel. "-np", "--parallel", "--n-parallel", @@ -201,9 +200,8 @@ def test_denylist_rejects_all_aliases(denied): @pytest.mark.parametrize( "args,offending", [ - # Pass-through --parallel would last-wins-override the real slot - # count while Unsloth's KV-cache fit + llama_parallel_slots stay at - # the typer value -- plan vs. process disagree. + # Pass-through --parallel would last-wins-override the real slot count + # while the KV-cache fit and slot bookkeeping stay at the resolved value. (["--parallel", "8"], "--parallel"), (["--parallel=8"], "--parallel"), (["--n-parallel", "16"], "--n-parallel"), @@ -213,7 +211,7 @@ def test_denylist_rejects_all_aliases(denied): # `["-np8"]` must still resolve to managed. (["-np8"], "-np"), (["-np64"], "-np"), - # Out-of-range values that would bypass the typer 1..64 guard. + # Out-of-range values that would bypass the PARALLEL_MIN/MAX bounds. (["--parallel", "999"], "--parallel"), (["-np", "0"], "-np"), (["-np999"], "-np"), @@ -300,7 +298,7 @@ def test_is_managed_flag_true_for_denied(): assert is_managed_flag("--api-key") is True assert is_managed_flag("-m") is True assert is_managed_flag("--model") is True - # Parallel slots owned by the typer --parallel flag. + # Parallel slots owned by typer --parallel and LoadRequest.n_parallel. assert is_managed_flag("--parallel") is True assert is_managed_flag("--n-parallel") is True assert is_managed_flag("-np") is True diff --git a/studio/backend/tests/test_mcp_flatten_result.py b/studio/backend/tests/test_mcp_flatten_result.py index 7daee799f9..618c5ccfe6 100644 --- a/studio/backend/tests/test_mcp_flatten_result.py +++ b/studio/backend/tests/test_mcp_flatten_result.py @@ -175,3 +175,46 @@ def test_call_tool_sync_passes_raise_on_error_false_and_keeps_error_images(monke assert out.startswith("Error: boom") assert MCP_IMAGES_SENTINEL in out assert is_tool_error(out) + + +def test_stdio_session_call_also_passes_raise_on_error_false(monkeypatch): + seen = {} + + class _FakeStdioClient: + def __init__(self): + self.connected = False + self.transport = SimpleNamespace(_is_session_dead = lambda: False) + + async def __aenter__(self): + self.connected = True + return self + + async def __aexit__(self, *exc): + self.connected = False + + def is_connected(self): + return self.connected + + async def call_tool( + self, + name, + args, + raise_on_error = True, + ): + seen["raise_on_error"] = raise_on_error + return _result(_text("boom"), _image(), is_error = True) + + monkeypatch.setattr( + mcp_client, "_client", lambda url, headers, use_oauth = False: _FakeStdioClient() + ) + try: + out = call_tool_sync( + "npx fake-stdio-server", None, "take_screenshot", {}, scope = "s=p:t=thread1" + ) + finally: + mcp_client.close_stdio_sessions() + + assert seen["raise_on_error"] is False + assert out.startswith("Error: boom") + assert MCP_IMAGES_SENTINEL in out + assert is_tool_error(out) diff --git a/studio/backend/tests/test_mcp_stdio_sessions.py b/studio/backend/tests/test_mcp_stdio_sessions.py index d714d9d640..37c812677a 100644 --- a/studio/backend/tests/test_mcp_stdio_sessions.py +++ b/studio/backend/tests/test_mcp_stdio_sessions.py @@ -60,7 +60,12 @@ class FakeClient: def is_connected(self) -> bool: return self.connected - async def call_tool(self, name: str, args: dict): + async def call_tool( + self, + name: str, + args: dict, + raise_on_error: bool = True, + ): if self.call_delay: await asyncio.sleep(self.call_delay) if self.fail_next: @@ -120,10 +125,15 @@ def test_tool_error_does_not_recycle_session(fake_clients, monkeypatch): from fastmcp.exceptions import ToolError class ToolFailure(FakeClient): - async def call_tool(self, name, args): + async def call_tool( + self, + name, + args, + raise_on_error = True, + ): if name == "boom": raise ToolError("tool exploded") # tool-level: session stays connected - return await super().call_tool(name, args) + return await super().call_tool(name, args, raise_on_error) monkeypatch.setattr( mcp_client, "_client", lambda url, headers, use_oauth = False: ToolFailure(url) @@ -441,12 +451,17 @@ def test_overlapping_calls_serialize_on_shared_session(fake_clients, monkeypatch active = 0 max_active = 0 - async def call_tool(self, name, args): + async def call_tool( + self, + name, + args, + raise_on_error = True, + ): OverlapDetect.active += 1 OverlapDetect.max_active = max(OverlapDetect.max_active, OverlapDetect.active) try: await asyncio.sleep(0.2) - return await super().call_tool(name, args) + return await super().call_tool(name, args, raise_on_error) finally: OverlapDetect.active -= 1 @@ -473,9 +488,14 @@ def test_timeout_budget_spans_connect_and_call(fake_clients, monkeypatch): await asyncio.sleep(0.4) return await super().__aenter__() - async def call_tool(self, name, args): + async def call_tool( + self, + name, + args, + raise_on_error = True, + ): await asyncio.sleep(0.5) - return await super().call_tool(name, args) + return await super().call_tool(name, args, raise_on_error) monkeypatch.setattr(mcp_client, "_client", lambda url, headers, use_oauth = False: SlowBoth(url)) start = time.monotonic() @@ -565,7 +585,11 @@ def test_execute_tool_config_check_tracks_row(tmp_path, monkeypatch): def test_multi_block_result_flattens_through_session(fake_clients): - async def _rich_call(name, args): + async def _rich_call( + name, + args, + raise_on_error = True, + ): return SimpleNamespace( content = [ SimpleNamespace(type = "text", text = "### Page"), diff --git a/studio/backend/tests/test_mtp_vram_budget.py b/studio/backend/tests/test_mtp_vram_budget.py index 77ca76325f..3742018e5e 100644 --- a/studio/backend/tests/test_mtp_vram_budget.py +++ b/studio/backend/tests/test_mtp_vram_budget.py @@ -817,7 +817,26 @@ class TestExtraArgsMtpDetection: ], ) def test_flash_attn_last_value_wins(self, args, expected): - assert _flash_attn_enabled_from_args(args) is expected + assert _flash_attn_enabled_from_args(args, env = {}) is expected + + @pytest.mark.parametrize( + "value,expected", + [ + ("off", False), + ("disabled", False), + ("false", False), + ("0", False), + ("on", True), + ("auto", True), + ("garbage", True), # llama.cpp refuses to start, so the default is moot + ], + ) + def test_flash_attn_env_applies(self, value, expected): + env = {"LLAMA_ARG_FLASH_ATTN": value} + assert _flash_attn_enabled_from_args([], env = env) is expected + # llama.cpp parses the environment first, so an explicit flag still wins. + assert _flash_attn_enabled_from_args(["-fa", "on"], env = env) is True + assert _flash_attn_enabled_from_args(["-fa", "off"], env = env) is False def test_effective_main_cache_types_follow_env_then_cli(self): env = { diff --git a/studio/backend/tests/test_parallel_slots_per_load.py b/studio/backend/tests/test_parallel_slots_per_load.py new file mode 100644 index 0000000000..f4f2d31c6f --- /dev/null +++ b/studio/backend/tests/test_parallel_slots_per_load.py @@ -0,0 +1,517 @@ +# SPDX-License-Identifier: AGPL-3.0-only +# Copyright 2026-present the Unsloth AI Inc. team. All rights reserved. See /studio/LICENSE.AGPL-3.0 + +"""Backend contract for the per-load parallel-slots knob. + +An optional ``n_parallel`` (llama-server ``--parallel``) rides on LoadRequest; +omitted, the server-wide launch default (``run.py --parallel``) applies. These +tests pin the pydantic contract and the shared PARALLEL_MIN/MAX mirrors, the +``requested_parallel_slots`` lifecycle, the ``_already_in_target_state`` +requested-vs-requested reload branch with its diffusion skip, and the route +wiring behind the /load, /validate and /status echoes. +""" + +from __future__ import annotations + +import inspect +import re +import struct +import sys +import types as _types +from pathlib import Path + +import pytest + +_BACKEND_DIR = str(Path(__file__).resolve().parent.parent) +if _BACKEND_DIR not in sys.path: + sys.path.insert(0, _BACKEND_DIR) + +# Same external-dep stubs as the other llama_cpp unit tests. +_loggers_stub = _types.ModuleType("loggers") +_loggers_stub.get_logger = lambda name: __import__("logging").getLogger(name) +sys.modules.setdefault("loggers", _loggers_stub) + +_structlog_stub = _types.ModuleType("structlog") +_structlog_stub.get_logger = lambda *a, **k: __import__("logging").getLogger("stub") +sys.modules.setdefault("structlog", _structlog_stub) + +# Real httpx: a stub would poison a combined run (routes/inference reads its +# attrs at def time). +import httpx # noqa: F401 + +from core.inference import llama_cpp as llama_cpp_module +from core.inference.llama_server_args import PARALLEL_MAX, PARALLEL_MIN +from core.inference.llama_cpp import LlamaCppBackend +from models.inference import ( + InferenceStatusResponse, + LoadRequest, + LoadResponse, + ValidateModelRequest, +) + + +class _FakeProcess: + def terminate(self): + pass + + def wait(self, timeout = None): + return 0 + + def kill(self): + pass + + def poll(self): + return 0 + + +# ── Pydantic contract ──────────────────────────────────────────────── + + +def test_load_request_defaults_n_parallel_none(): + assert LoadRequest(model_path = "owner/repo").n_parallel is None + + +@pytest.mark.parametrize("value", [PARALLEL_MIN, 4, PARALLEL_MAX]) +def test_load_request_accepts_in_range_n_parallel(value): + assert LoadRequest(model_path = "owner/repo", n_parallel = value).n_parallel == value + + +@pytest.mark.parametrize("value", [0, -1, PARALLEL_MAX + 1]) +def test_load_request_rejects_out_of_range_n_parallel(value): + with pytest.raises(ValueError): + LoadRequest(model_path = "owner/repo", n_parallel = value) + + +def test_load_request_round_trips_json_key(): + req = LoadRequest.model_validate({"model_path": "owner/repo", "n_parallel": 8}) + assert req.n_parallel == 8 + assert req.model_dump()["n_parallel"] == 8 + + +def test_validate_request_n_parallel_contract(): + # /validate sizes like /load, so it carries the same field and bounds. + assert ValidateModelRequest(model_path = "owner/repo").n_parallel is None + assert ( + ValidateModelRequest(model_path = "owner/repo", n_parallel = PARALLEL_MAX).n_parallel + == PARALLEL_MAX + ) + with pytest.raises(ValueError): + ValidateModelRequest(model_path = "owner/repo", n_parallel = PARALLEL_MAX + 1) + + +@pytest.mark.parametrize("model_cls", [LoadResponse, InferenceStatusResponse]) +def test_response_models_emit_parallel_slot_fields(model_cls): + kwargs = ( + dict(status = "loaded", model = "owner/repo", display_name = "repo", inference = {}) + if model_cls is LoadResponse + else {} + ) + empty = model_cls(**kwargs).model_dump() + assert empty["requested_parallel_slots"] is None + assert empty["parallel_slots"] is None + dumped = model_cls(**kwargs, requested_parallel_slots = 8, parallel_slots = 4).model_dump() + assert dumped["requested_parallel_slots"] == 8 + assert dumped["parallel_slots"] == 4 + + +# ── Shared bounds and their deliberate mirrors ─────────────────────── + + +def _mirrored_bounds(source_path: Path) -> tuple[int, int]: + src = source_path.read_text(encoding = "utf-8") + low = re.search(r"^_PARALLEL_MIN\s*=\s*(\d+)$", src, re.MULTILINE) + high = re.search(r"^_PARALLEL_MAX\s*=\s*(\d+)$", src, re.MULTILINE) + assert low and high, f"{source_path} must define _PARALLEL_MIN/_PARALLEL_MAX" + return int(low.group(1)), int(high.group(1)) + + +def test_run_py_mirror_matches_shared_bounds(): + assert _mirrored_bounds(Path(_BACKEND_DIR) / "run.py") == (PARALLEL_MIN, PARALLEL_MAX) + + +def test_cli_mirror_matches_shared_bounds(): + cli = Path(_BACKEND_DIR).parent.parent / "unsloth_cli" / "commands" / "studio.py" + assert _mirrored_bounds(cli) == (PARALLEL_MIN, PARALLEL_MAX) + + +def test_frontend_mirror_matches_shared_bounds(): + # The UI clamps with its own copy; a bumped PARALLEL_MAX that skips it would + # leave the UI silently capping lower. + src = ( + Path(_BACKEND_DIR).parent + / "frontend" + / "src" + / "features" + / "model-picker" + / "model-config" + / "per-model-config.ts" + ).read_text(encoding = "utf-8") + low = re.search(r"^export const N_PARALLEL_MIN = (\d+);$", src, re.MULTILINE) + high = re.search(r"^export const N_PARALLEL_MAX = (\d+);$", src, re.MULTILINE) + assert low and high, "per-model-config.ts must export N_PARALLEL_MIN/MAX" + assert (int(low.group(1)), int(high.group(1))) == (PARALLEL_MIN, PARALLEL_MAX) + + +def test_preset_model_reuses_shared_bounds(): + # Bounds drifting from PARALLEL_MIN/MAX would 422 valid presets on every sync. + from routes.chat_history import ChatPresetLoadConfig + + field = ChatPresetLoadConfig.model_fields["nParallel"] + bounds = {type(m).__name__: getattr(m, "ge", getattr(m, "le", None)) for m in field.metadata} + assert bounds.get("Ge") == PARALLEL_MIN + assert bounds.get("Le") == PARALLEL_MAX + + +# ── requested_parallel_slots lifecycle ─────────────────────────────── + + +@pytest.fixture +def backend(monkeypatch): + monkeypatch.setattr(LlamaCppBackend, "_kill_orphaned_servers", lambda self: 0) + monkeypatch.setattr(llama_cpp_module.atexit, "register", lambda *_args, **_kwargs: None) + return LlamaCppBackend() + + +def test_requested_parallel_slots_initial_value_is_one(backend): + assert backend.requested_parallel_slots == 1 + + +def test_requested_parallel_slots_reflects_field(backend): + backend._requested_n_parallel = 8 + assert backend.requested_parallel_slots == 8 + + +@pytest.mark.parametrize("value", [None, 0, -2, "not-an-int"]) +def test_requested_parallel_slots_invalid_value_falls_back_to_one(backend, value): + backend._requested_n_parallel = value + assert backend.requested_parallel_slots == 1 + + +def test_reset_effective_parallel_slots_also_resets_requested(backend): + backend._requested_n_parallel = 8 + backend._commit_effective_parallel_slots(4) + + backend._reset_effective_parallel_slots() + + assert backend.requested_parallel_slots == 1 + assert backend.effective_parallel_slots == 1 + + +def test_unload_resets_requested_parallel_slots(backend): + backend._process = _FakeProcess() + backend._requested_n_parallel = 8 + + backend.unload_model() + + assert backend.requested_parallel_slots == 1 + + +def test_load_model_commits_requested_from_pending_kwargs(): + # n_parallel may be reduced before the commit, so the requested value must + # come from the pre-reduction pending snapshot. + src = inspect.getsource(LlamaCppBackend.load_model) + commit = src.find( + 'self._requested_n_parallel = max(1, int(_pending_load_kwargs["n_parallel"]))' + ) + healthy = src.find("self._healthy = True\n", 0, commit if commit != -1 else None) + snapshot = src.find("self._last_load_kwargs = _pending_load_kwargs") + assert commit != -1, "load_model must commit the requested slot count" + assert healthy != -1 and healthy < commit < snapshot + + +# ── _already_in_target_state requested-vs-requested branch ─────────── + + +def _loaded_backend() -> LlamaCppBackend: + backend = LlamaCppBackend() + backend._process = _FakeProcess() # is_loaded only checks "is not None" + backend._healthy = True + backend._model_identifier = "owner/repo" + backend._hf_variant = "Q4_K_M" + backend._requested_n_ctx = 8192 + backend._cache_type_kv = None + backend._requested_spec_mode = "auto" + backend._chat_template_override = None + backend._is_vision = False + backend._extra_args = None + backend._gguf_path = None + return backend + + +def _target_state(backend: LlamaCppBackend, n_parallel: int) -> bool: + return backend._already_in_target_state( + gguf_path = None, + model_identifier = "owner/repo", + hf_variant = "Q4_K_M", + n_ctx = 8192, + cache_type_kv = None, + speculative_type = "auto", + chat_template_override = None, + extra_args = None, + is_vision = False, + n_parallel = n_parallel, + ) + + +def test_already_in_target_state_matches_same_slots(): + backend = _loaded_backend() + backend._requested_n_parallel = 4 + assert _target_state(backend, 4) is True + + +def test_already_in_target_state_reloads_on_slots_change(): + backend = _loaded_backend() + backend._requested_n_parallel = 4 + assert _target_state(backend, 8) is False + + +def test_already_in_target_state_compares_requested_not_effective(): + # An identical re-Apply must dedupe even after the fitter reduced the slots. + backend = _loaded_backend() + backend._requested_n_parallel = 8 + backend._commit_effective_parallel_slots(4) + assert _target_state(backend, 8) is True + + +def test_already_in_target_state_ignores_slots_for_diffusion(): + # The diffusion runner ignores --parallel, so a slots change must not reload. + backend = _loaded_backend() + backend._is_diffusion = True + backend._requested_n_parallel = 1 + assert _target_state(backend, 8) is True + + +# ── Route wiring (source contract, mirroring test_gpu_memory_mode) ─── + + +def _route_source() -> str: + return (Path(_BACKEND_DIR) / "routes" / "inference.py").read_text(encoding = "utf-8") + + +def _load_impl_source() -> str: + """Body of _load_model_impl only, so positional assertions can't be + satisfied by a later function in the module.""" + src = _route_source() + body = src[src.index("async def _load_model_impl") :] + return body[: body.index("\n@router.")] + + +def test_route_resolves_slots_once_before_dedupe_guard_and_load(): + load_impl = _load_impl_source() + resolve = load_impl.index("request.n_parallel") + fallback = load_impl.index('getattr(_app_state, "llama_parallel_slots", 1)') + dedupe = load_impl.index("requested_parallel_slots = _n_parallel") + guard = load_impl.index("_guard_chat_load_against_training") + # The GGUF launch kwargs, not the guard's own kwarg (which shares the spelling). + load_kwargs = load_impl.index("_common_load_kwargs = dict(") + assert resolve < dedupe, "resolution must precede the reload dedupe" + assert fallback < dedupe + assert resolve < guard < load_kwargs + # Guard and load kwargs share the resolved value; app.state is read once. + assert load_impl.count("n_parallel = _n_parallel") == 2 + assert "n_parallel = _n_parallel" in load_impl[load_kwargs : load_kwargs + 800] + assert load_impl.count('getattr(_app_state, "llama_parallel_slots", 1)') == 1 + # getattr, so a direct caller without an app cannot raise, and no re-read. + assert "fastapi_request.app.state" not in load_impl + + +def test_route_dedupe_compares_requested_slots_and_skips_diffusion(): + match_impl = _route_source()[_route_source().index("def _request_matches_loaded_settings") :] + match_impl = match_impl[: match_impl.index("\ndef ")] + assert "requested_parallel_slots is not None" in match_impl + assert "not llama_backend.is_diffusion" in match_impl + assert "llama_backend.requested_parallel_slots" in match_impl + + +def test_route_echoes_requested_and_effective_slots(): + route_src = _route_source() + # Both /load returns plus the /status GGUF branch, via the shared helper. + assert route_src.count("**_parallel_slot_echo(llama_backend)") == 3 + + +def test_parallel_slot_echo_reports_none_for_diffusion(): + # Diffusion never commits a count, so echoing the reset placeholder 1 would lie. + from routes.inference import _parallel_slot_echo + + backend = _loaded_backend() + backend._requested_n_parallel = 8 + backend._commit_effective_parallel_slots(4) + assert _parallel_slot_echo(backend) == {"requested_parallel_slots": 8, "parallel_slots": 4} + backend._is_diffusion = True + assert _parallel_slot_echo(backend) == { + "requested_parallel_slots": None, + "parallel_slots": None, + } + + +def test_validate_route_prefers_request_n_parallel(): + validate_impl = _route_source()[_route_source().index("async def validate_model") :] + resolve = validate_impl.index("request.n_parallel") + fallback = validate_impl.index('"llama_parallel_slots",') + guard = validate_impl.index("_guard_chat_load_against_training") + assert guard < resolve and guard < fallback, "the guard call resolves the slots inline" + + +def _load_model_source() -> str: + return inspect.getsource(LlamaCppBackend.load_model) + + +def test_slots_fall_back_to_one_without_kv_unified(): + # Without --kv-unified llama-server gives each slot -c/N, so an explicit + # --parallel N shrinks every context window. + src = _load_model_source() + clamp = src.find("supports_kv_unified") + assert clamp != -1, "load_model must check for --kv-unified before honouring the slots" + block = src[clamp : clamp + 700] + assert ( + "n_parallel > 1" in src[clamp - 300 : clamp] + ), "only an explicit multi-slot load is clamped" + assert "n_parallel = 1" in block + + +def test_clamp_sits_between_the_echo_and_the_fit(): + # The echo reports the ask and the fit uses what launches, so the clamp + # belongs between the two. + src = _load_model_source() + pending = src.index("_pending_load_kwargs") + clamp = src.index("supports_kv_unified") + estimate = src.index("_estimate") + commit = src.index("_commit_effective_parallel_slots") + assert pending < clamp, "the requested count is captured before the clamp" + assert clamp < estimate, "the fit must be estimated from the effective slot count" + assert clamp < commit, "the committed effective count is the clamped one" + + +# ── Training-guard sizing ──────────────────────────────────────────── + + +def _write_swa_gguf(path: Path) -> str: + """Smallest DiffusionGemma-shaped header the KV estimator can size: the + canvas marker routing it to the diffusion runner, plus the sliding-window + dims that make llama.cpp's SWA cache slot-scaled.""" + + def _kv_str(key: str, value: str) -> bytes: + kb, vb = key.encode(), value.encode() + return ( + struct.pack(" bytes: + kb = key.encode() + return struct.pack(" float: + """Run the training guard over a local GGUF and return the size it budgeted.""" + import routes.inference as inf + + seen = {} + + core_training = _types.ModuleType("core.training") + core_training.get_training_backend = lambda: _types.SimpleNamespace( + is_training_active = lambda: True + ) + + def _can_load(**kwargs): + seen.update(kwargs) + return True, {"mode": "single_device"} + + training_vram = _types.ModuleType("routes.training_vram") + training_vram.can_load_chat_during_training = _can_load + monkeypatch.setitem(sys.modules, "core.training", core_training) + monkeypatch.setitem(sys.modules, "routes.training_vram", training_vram) + + monkeypatch.setattr(inf, "_classify_diffusion_gguf", lambda _config: diffusion) + monkeypatch.setattr(LlamaCppBackend, "_is_vulkan_backend", staticmethod(lambda *a, **k: False)) + monkeypatch.setattr(LlamaCppBackend, "_effective_gpu_count", staticmethod(lambda *a, **k: 1)) + monkeypatch.setattr(LlamaCppBackend, "_diffusion_gpu_arg", staticmethod(lambda *a, **k: "0")) + # Pin the --kv-unified probe so the estimate cannot depend on a locally + # installed llama-server. Default "no binary found" leaves the count alone. + monkeypatch.setattr( + LlamaCppBackend, + "probe_server_capabilities", + classmethod(lambda cls, binary = None: dict(caps or {})), + ) + + inf._guard_chat_load_against_training( + _types.SimpleNamespace(is_gguf = True, gguf_file = gguf_path, identifier = "local/model"), + model_identifier = "local/model", + hf_token = None, + load_in_4bit = False, + max_seq_length = 8192, + requested_gpu_ids = None, + n_parallel = n_parallel, + gpu_memory_mode = "auto", + ) + return seen["required_override_gb"] + + +def test_training_guard_sizes_a_diffusion_gguf_at_one_slot(monkeypatch, tmp_path): + # Diffusion ignores --parallel, so slots must not inflate the estimate and 409 + # a load that would have fitted beside training. + gguf = _write_swa_gguf(tmp_path / "diffusion.gguf") + one = _guard_required_gb(monkeypatch, gguf, n_parallel = 1, diffusion = True) + many = _guard_required_gb(monkeypatch, gguf, n_parallel = 8, diffusion = True) + assert one == many + + +def test_training_guard_still_sizes_slots_for_an_ordinary_gguf(monkeypatch, tmp_path): + # llama-server does allocate per-slot SWA cells, so the reduction above must + # be scoped to diffusion and not flatten every GGUF to one slot. + gguf = _write_swa_gguf(tmp_path / "chat.gguf") + one = _guard_required_gb(monkeypatch, gguf, n_parallel = 1, diffusion = False) + many = _guard_required_gb(monkeypatch, gguf, n_parallel = 8, diffusion = False) + assert many > one + + +def test_training_guard_sizes_one_slot_when_the_binary_has_no_kv_unified(monkeypatch, tmp_path): + # load_model clamps a multi-slot request to 1 on such a build, where each slot + # carries its own SWA stream, so sizing the asked count would 409 a load that fits. + gguf = _write_swa_gguf(tmp_path / "chat.gguf") + old = {"found": True, "supports_kv_unified": False} + one = _guard_required_gb(monkeypatch, gguf, n_parallel = 1, diffusion = False, caps = old) + many = _guard_required_gb(monkeypatch, gguf, n_parallel = 8, diffusion = False, caps = old) + assert one == many + + +def test_training_guard_sizes_every_slot_when_kv_unified_exists(monkeypatch, tmp_path): + # The clamp is scoped to binaries that cannot serve the slots; a capable one + # really does allocate the SWA window per slot. + gguf = _write_swa_gguf(tmp_path / "chat.gguf") + new = {"found": True, "supports_kv_unified": True} + one = _guard_required_gb(monkeypatch, gguf, n_parallel = 1, diffusion = False, caps = new) + many = _guard_required_gb(monkeypatch, gguf, n_parallel = 8, diffusion = False, caps = new) + assert many > one + + +def test_training_guard_keeps_slots_for_an_unclassified_gguf(monkeypatch, tmp_path): + # None = inconclusive header, so keep the larger estimate rather than + # under-size against training. + gguf = _write_swa_gguf(tmp_path / "unknown.gguf") + one = _guard_required_gb(monkeypatch, gguf, n_parallel = 1, diffusion = None) + many = _guard_required_gb(monkeypatch, gguf, n_parallel = 8, diffusion = None) + assert many > one diff --git a/studio/backend/tests/test_safetensors_tool_loop.py b/studio/backend/tests/test_safetensors_tool_loop.py index 1043005f64..2e7e99fbba 100644 --- a/studio/backend/tests/test_safetensors_tool_loop.py +++ b/studio/backend/tests/test_safetensors_tool_loop.py @@ -24,6 +24,7 @@ from core.inference.safetensors_agentic import ( strip_tool_markup_streaming, ) from core.inference.tool_call_parser import ( + NUDGE_TOOL_CALLS_STATUS, RAG_MAX_SEARCHES_PER_TURN, has_tool_signal, parse_tool_calls_from_text, @@ -2231,6 +2232,24 @@ def test_reprompt_names_only_active_tools_not_hardcoded(): assert "python" not in reprompt["content"] +def test_reprompt_is_announced_on_the_status_channel(): + # The re-prompted turn is hidden, so the badge is the only sign of life. + # Blank still comes first: the route resets its text cursor only on that. + _captured, events = _reprompt_loop(auto_heal_tool_calls = True) + statuses = [e["text"] for e in events if e["type"] == "status"] + assert NUDGE_TOOL_CALLS_STATUS in statuses + index = statuses.index(NUDGE_TOOL_CALLS_STATUS) + # index > 0 matters: at 0, statuses[-1] wraps to the terminal clear. + assert index > 0 and statuses[index - 1] == "" + assert statuses[-1] == "" + + +def test_reprompt_status_absent_without_a_nudge(): + _captured, events = _reprompt_loop(auto_heal_tool_calls = False) + statuses = [e["text"] for e in events if e["type"] == "status"] + assert NUDGE_TOOL_CALLS_STATUS not in statuses + + def test_reprompt_suppressed_when_auto_heal_disabled(): # With Auto-Heal off the safetensors nudge must stay silent for backend parity # with the GGUF loop, so only the single initial generation runs. diff --git a/studio/frontend/src/components/assistant-ui/thread.tsx b/studio/frontend/src/components/assistant-ui/thread.tsx index 6da8126421..9b3c7aa79e 100644 --- a/studio/frontend/src/components/assistant-ui/thread.tsx +++ b/studio/frontend/src/components/assistant-ui/thread.tsx @@ -91,6 +91,7 @@ import { useResearchRunStore, } from "@/features/chat/stores/research-run-store"; import { parseExternalModelId } from "@/features/chat/external-providers"; +import { toolStatusKind } from "@/features/chat/utils/tool-status"; import { McpComposerButton } from "@/features/chat/mcp-composer-button"; import { getExternalReasoningCapabilities } from "@/features/chat/provider-capabilities"; import { useRagToolDisabled } from "@/features/chat/hooks/use-rag-tool-disabled"; @@ -2847,15 +2848,28 @@ const ToolStatusDisplay: FC = () => { } // From the store's start time, so returning to the conversation resumes rather than restarting. const elapsed = Math.max(0, Math.floor((now - startedAt) / 1000)); - const isRunning = toolStatus.startsWith("Running"); - const StatusIcon = isRunning ? TerminalIcon : GlobeIcon; + const kind = toolStatusKind(toolStatus); + const isNudging = kind === "nudge"; + const StatusIcon = kind === "terminal" ? TerminalIcon : GlobeIcon; return (
-
- +
+ {isNudging ? ( + // label, not the default "Loading": the spinner is the badge's only + // role="status" region, so its name is what gets announced. + + ) : ( + + )} {toolStatus} {elapsed}s
diff --git a/studio/frontend/src/features/chat/api/chat-adapter.ts b/studio/frontend/src/features/chat/api/chat-adapter.ts index 08d17f2a65..5f6c6cc589 100644 --- a/studio/frontend/src/features/chat/api/chat-adapter.ts +++ b/studio/frontend/src/features/chat/api/chat-adapter.ts @@ -1604,6 +1604,7 @@ async function autoLoadSmallestModel(): Promise<{ ? { gpu_ids: effectiveGpuIds ?? undefined, gpu_memory_mode: effectiveGpuMemoryMode, + n_parallel: config.nParallel ?? null, } : {}), })) @@ -1637,6 +1638,8 @@ async function autoLoadSmallestModel(): Promise<{ gpu_layers: effectiveGpuLayers, n_cpu_moe: effectiveNCpuMoe, gpu_ids: effectiveGpuIds ?? undefined, + // Per-model too, or the auto-load reverts a remembered override. + n_parallel: config.nParallel ?? null, } : {}), }); @@ -1689,6 +1692,11 @@ async function autoLoadSmallestModel(): Promise<{ effectiveGpuLayers, config.customContextLength ?? null, ); + // Slots this auto-load committed. Diffusion ignores --parallel, so a count + // there would mint a phantom override a saved preset carries onto a GGUF. + const committedSlots = (loadResp.is_diffusion ?? false) + ? null + : (config.nParallel ?? null); useChatRuntimeStore.setState({ ggufContextLength: loadResp.context_length ?? 131072, ggufMaxContextLength: @@ -1703,6 +1711,9 @@ async function autoLoadSmallestModel(): Promise<{ ...resolveToolsEnabledOnLoad(loadResp.supports_tools ?? false), kvCacheDtype: loadResp.cache_type_kv ?? null, loadedKvCacheDtype: loadResp.cache_type_kv ?? null, + // Click-time value, not the resolved backend echo (see performLoad). + nParallel: committedSlots, + loadedNParallel: committedSlots, tensorParallel: loadResp.tensor_parallel ?? false, loadedTensorParallel: loadResp.tensor_parallel ?? false, ...loadedGpuMemoryFields(loadResp), @@ -1728,6 +1739,10 @@ async function autoLoadSmallestModel(): Promise<{ ...resolveToolsEnabledOnLoad(loadResp.supports_tools ?? false), kvCacheDtype: loadResp.cache_type_kv ?? null, loadedKvCacheDtype: loadResp.cache_type_kv ?? null, + // GGUF-only and never sent here: a staged override would be saved for + // a model that cannot use it. + nParallel: null, + loadedNParallel: null, tensorParallel: loadResp.tensor_parallel ?? false, loadedTensorParallel: loadResp.tensor_parallel ?? false, // Non-GGUF response: clears any stale GPU baseline a prior manual-GPU @@ -2001,6 +2016,10 @@ async function autoLoadSmallestModel(): Promise<{ ...resolveToolsEnabledOnLoad(loadResp.supports_tools ?? false), kvCacheDtype: loadResp.cache_type_kv ?? null, loadedKvCacheDtype: loadResp.cache_type_kv ?? null, + // The request above omits n_parallel: a staged override left from a + // preset would read as applied and be re-sent by the next Apply. + nParallel: null, + loadedNParallel: null, tensorParallel: loadResp.tensor_parallel ?? false, loadedTensorParallel: loadResp.tensor_parallel ?? false, ...loadedGpuMemoryFields(loadResp), diff --git a/studio/frontend/src/features/chat/api/chat-api.ts b/studio/frontend/src/features/chat/api/chat-api.ts index 60b737fb68..8ad2691391 100644 --- a/studio/frontend/src/features/chat/api/chat-api.ts +++ b/studio/frontend/src/features/chat/api/chat-api.ts @@ -192,6 +192,8 @@ export async function validateModel( // --fit, while a pinned layer count is owned by the user. Tell validate // so it applies the same training-guard policy as /load. gpu_memory_mode: payload.gpu_memory_mode, + // Slots scale the KV estimate; keep validate sized like the load. + n_parallel: payload.n_parallel, }), }); return parseJsonOrThrow(response); diff --git a/studio/frontend/src/features/chat/artifacts/artifact-surface.tsx b/studio/frontend/src/features/chat/artifacts/artifact-surface.tsx index 1955c3aca1..4e28e7f457 100644 --- a/studio/frontend/src/features/chat/artifacts/artifact-surface.tsx +++ b/studio/frontend/src/features/chat/artifacts/artifact-surface.tsx @@ -30,7 +30,7 @@ import { Streamdown } from "streamdown"; import { ArtifactHtmlFrame, type ArtifactViewMode } from "./html-frame"; import { useChatArtifactsStore } from "./store"; import type { ChatArtifact } from "./types"; -import { getArtifactFilename } from "./types"; +import { buildArtifactSourceKey, getArtifactFilename } from "./types"; const COPY_RESET_MS = 2000; const artifactSourceCodePlugin = createCodePlugin({ @@ -338,6 +338,8 @@ export function ArtifactSurface({ ) : (
>> 0).toString(36); } +// The canvas source view keys its Streamdown on this. Streamdown memoizes a code +// fence on its node's line/column span, ignoring the text, so equal-line-count +// canvases keep the old source. Tool artifact IDs omit the code, so hash it in. +export function buildArtifactSourceKey( + artifact: Pick, +): string { + return `${artifact.id}:${hashArtifactCode(artifact.code)}`; +} + export function createArtifactId(input: ChatArtifactInput): string { const threadSegment = input.threadId || "no-thread"; const messageSegment = input.sourceMessageId || "transient"; diff --git a/studio/frontend/src/features/chat/chat-settings-sheet.tsx b/studio/frontend/src/features/chat/chat-settings-sheet.tsx index 7b310c50d4..6070bd2e40 100644 --- a/studio/frontend/src/features/chat/chat-settings-sheet.tsx +++ b/studio/frontend/src/features/chat/chat-settings-sheet.tsx @@ -397,6 +397,7 @@ export function ChatSettingsPanel({ const nCpuMoe = useChatRuntimeStore((s) => s.nCpuMoe); const tensorParallel = useChatRuntimeStore((s) => s.tensorParallel); const specDraftNMax = useChatRuntimeStore((s) => s.specDraftNMax); + const nParallel = useChatRuntimeStore((s) => s.nParallel); const speculativeType = useChatRuntimeStore((s) => s.speculativeType); const specFallbackReason = useChatRuntimeStore((s) => s.specFallbackReason); const mtpUpdatable = @@ -504,6 +505,7 @@ export function ChatSettingsPanel({ tensorParallel, speculativeType, specDraftNMax, + nParallel, params.maxSeqLength, ]); const activePresetLoadSummary = useMemo( @@ -522,6 +524,7 @@ export function ChatSettingsPanel({ tensorParallel, speculativeType, specDraftNMax, + nParallel, params.maxSeqLength, ], ); diff --git a/studio/frontend/src/features/chat/hooks/use-chat-model-runtime.ts b/studio/frontend/src/features/chat/hooks/use-chat-model-runtime.ts index bc7227e70d..5f0149d909 100644 --- a/studio/frontend/src/features/chat/hooks/use-chat-model-runtime.ts +++ b/studio/frontend/src/features/chat/hooks/use-chat-model-runtime.ts @@ -567,6 +567,8 @@ export function useChatModelRuntime() { applyActiveModelStatusToStore(residentStatus, { previousCheckpoint: selectedCheckpoint, previousGgufVariant, + // Id and variant matched above: same model, only the tab moved. + readoptingSameModel: true, }); syncModelCapabilities(modelId, residentStatus); return; @@ -669,6 +671,14 @@ export function useChatModelRuntime() { let previousWasUnloaded = false; const pendingLoadConfig = typeof selection !== "string" ? selection.config : undefined; + // The outgoing model's slot INTENT (blank = follow the server + // default), which the resolved baseline cannot express. previousConfig + // is the snapshot the picker took before pre-applying the target's + // config, so the live control is only the outgoing one without it. + const previousNParallel = + typeof selection !== "string" && selection.previousConfig + ? (selection.previousConfig.nParallel ?? null) + : useChatRuntimeStore.getState().nParallel; if (pendingLoadConfig) { applyPerModelConfigToRuntime(pendingLoadConfig); } @@ -761,6 +771,8 @@ export function useChatModelRuntime() { : stateBeforeUnload.speculativeType; let loadSpecDraftNMax = pendingLoadConfig?.specDraftNMax ?? stateBeforeUnload.specDraftNMax; + let loadNParallel = + pendingLoadConfig?.nParallel ?? stateBeforeUnload.nParallel; try { // Lightweight pre-flight validation: avoid unloading a working model // if the new identifier is clearly invalid (e.g. bad HF id / path). @@ -792,6 +804,10 @@ export function useChatModelRuntime() { const validateGpuLayers = resetsPerModelSettings ? GPU_LAYERS_AUTO : loadGpuLayers; + // Per-model: the reset re-baselines to the staged config, like the load. + const validateNParallel = resetsPerModelSettings + ? (pendingLoadConfig?.nParallel ?? null) + : loadNParallel; const validateMaxSeqLength = resolveFitMaxSeqLength( isGguf, loadGpuMemoryMode, @@ -820,7 +836,12 @@ export function useChatModelRuntime() { cache_type_kv: loadKvCacheDtype, tensor_parallel: loadTensorParallel, gpu_ids: validateGpuIds ?? undefined, - ...(isGguf ? { gpu_memory_mode: loadGpuMemoryMode } : {}), + ...(isGguf + ? { + gpu_memory_mode: loadGpuMemoryMode, + n_parallel: validateNParallel, + } + : {}), }); // Upgrade consent runs before the security dialogs; Accept installs and the load continues. if (validation.requires_transformers_upgrade) { @@ -903,6 +924,10 @@ export function useChatModelRuntime() { loadedSpeculativeType: persistedSpeculativeType, specDraftNMax: null, loadedSpecDraftNMax: null, + // Per-model too: a different model follows the server default + // unless its staged config overrides it. + nParallel: null, + loadedNParallel: null, // Per-model GPU knobs must not follow onto a different model // (gpuMemoryMode is a standing preference and is kept). selectedGpuIds: null, @@ -918,6 +943,7 @@ export function useChatModelRuntime() { ? normalizeSpeculativeType(pendingLoadConfig.speculativeType) : persistedSpeculativeType; loadSpecDraftNMax = pendingLoadConfig?.specDraftNMax ?? null; + loadNParallel = pendingLoadConfig?.nParallel ?? null; // Keep the click-time snapshot in lock-step with the store reset so // the load below sizes against the cleared per-model knobs, not the // previous model's (gpuMemoryMode is standing, so left as captured). @@ -984,6 +1010,8 @@ export function useChatModelRuntime() { cache_type_kv: loadKvCacheDtype, speculative_type: loadSpeculativeType, spec_draft_n_max: loadSpecDraftNMax, + // GGUF-only: slots mean nothing for a transformers load. + n_parallel: isGguf ? loadNParallel : null, tensor_parallel: loadTensorParallel, gpu_memory_mode: loadGpuMemoryMode, gpu_layers: loadGpuLayers, @@ -1034,6 +1062,14 @@ export function useChatModelRuntime() { const loadedSpec = normalizeSpeculativeType( loadResponse.speculative_type, ); + // Slots the load actually committed. Non-GGUF never sends them and + // diffusion ignores --parallel, so a click-time count on either + // would mint a phantom override a saved preset carries onto a GGUF. + const committedSlots = + (loadResponse.is_gguf ?? false) && + !(loadResponse.is_diffusion ?? false) + ? (loadNParallel ?? null) + : null; const nativeCtx = loadResponse.is_gguf ? (loadResponse.context_length ?? 131072) : null; @@ -1109,6 +1145,10 @@ export function useChatModelRuntime() { loadedSpeculativeType: loadedSpec, specDraftNMax: loadResponse.spec_draft_n_max ?? null, loadedSpecDraftNMax: loadResponse.spec_draft_n_max ?? null, + // Keep the click-time value: the echo is the resolved count, and + // adopting it would pin a blank "server default" control. + nParallel: committedSlots, + loadedNParallel: committedSlots, customContextLength: keepCustomCtx, loadedCustomContextLength: keepCustomCtx, defaultChatTemplate: loadResponse.chat_template ?? null, @@ -1211,6 +1251,7 @@ export function useChatModelRuntime() { stateBeforeUnload.loadedSpeculativeType, spec_draft_n_max: stateBeforeUnload.loadedSpecDraftNMax, + n_parallel: stateBeforeUnload.loadedNParallel, // Restore the previous model in the split mode it was running, // not the default layer split. tensor_parallel: stateBeforeUnload.loadedTensorParallel ?? false, @@ -1237,6 +1278,9 @@ export function useChatModelRuntime() { // model's; the loaded baselines below come from its reload echo. speculativeType: stateBeforeUnload.loadedSpeculativeType ?? null, specDraftNMax: stateBeforeUnload.loadedSpecDraftNMax ?? null, + // Control keeps its intent; only the baseline takes the echo. + nParallel: previousNParallel, + loadedNParallel: stateBeforeUnload.loadedNParallel ?? null, loadedSpeculativeType: rollbackSpeculativeType, loadedSpecDraftNMax: rollbackResponse.spec_draft_n_max ?? null, diff --git a/studio/frontend/src/features/chat/lib/apply-inference-status-to-store.ts b/studio/frontend/src/features/chat/lib/apply-inference-status-to-store.ts index f85ff3246b..47d40009c8 100644 --- a/studio/frontend/src/features/chat/lib/apply-inference-status-to-store.ts +++ b/studio/frontend/src/features/chat/lib/apply-inference-status-to-store.ts @@ -1,6 +1,9 @@ // SPDX-License-Identifier: AGPL-3.0-only // Copyright 2026-present the Unsloth AI Inc. team. All rights reserved. See /studio/LICENSE.AGPL-3.0 +// Barrel import (lint rule); the model-picker cycle is fine because the call +// happens at runtime, not module eval. +import { resolveInitialConfig } from "@/features/model-picker"; import { getInferenceStatus } from "../api/chat-api"; import { mergeBackendRecommendedInference, @@ -131,6 +134,9 @@ export type ApplyInferenceStatusOptions = { * status -- without it a variant-only switch underneath the tab reads as * steady state and the hydration reseed keeps the old quant's baselines. */ previousGgufVariant?: string | null; + /** The caller verified the status is the model this tab just picked, so the + * slot control it holds belongs to that model and must survive. */ + readoptingSameModel?: boolean; }; /** Mirror refresh() hydration so adopted CLI models get reasoning/tools flags. */ @@ -201,6 +207,22 @@ export function applyActiveModelStatusToStore( // While a load is in flight, performLoad owns the load params. Seeding them // from a stale poll here would clobber the values the load dialog just set. const seedLoadParams = !prevState.modelLoading; + // A model/variant change underneath this tab, as opposed to re-adopting the + // model the tab just picked, where hydratingExistingModel fires on the stale + // checkpoint. The echo cannot stand in: a new model can report the old count. + const slotsModelChanged = + hydratingExistingModel && !options.readoptingSameModel; + // This model's remembered override, read only on a fresh store or a model + // change, so a steady poll cannot re-pin a control the user just blanked. + const slotsUnseeded = + prevState.loadedNParallel === null && prevState.nParallel === null; + const remembered = + status.is_gguf && (slotsUnseeded || slotsModelChanged) + ? resolveInitialConfig(checkpointId, status.gguf_variant ?? null) + : null; + const rememberedNParallel = remembered?.remembered + ? (remembered.config.nParallel ?? null) + : null; // A Manual + Auto-layers load sent its positive context pin as max_seq_length, // and status only exposes the RESOLVED context; re-seed the pin from the // requested value (parity with the load paths' keepCustomCtx). Baselines @@ -322,6 +344,35 @@ export function applyActiveModelStatusToStore( tensorParallel: status.tensor_parallel, loadedTensorParallel: status.tensor_parallel, }), + // Baseline only, never the control: the echo is the RESOLVED count and would + // pin a blank "server default" control. The rollback re-sends the baseline, + // so without this a rollback after a tab reload loses the override. + ...(seedLoadParams && + status.requested_parallel_slots != null && + (prevState.loadedNParallel === null || hydratingExistingModel) && { + loadedNParallel: status.requested_parallel_slots, + }), + // A slotless model must not keep the previous GGUF's baseline: the rollback + // re-sends it. /status omits the echo for non-GGUF and sends an explicit + // null for diffusion, so an absent field on a GGUF is an older backend. + ...(seedLoadParams && + (status.is_gguf === false || status.requested_parallel_slots === null) && { + loadedNParallel: null, + }), + // Per-model: a change underneath this tab blanks the control like + // performLoad's cross-model reset, or the old count follows onto the new + // model. The baseline above still carries the rollback. + ...(seedLoadParams && slotsModelChanged && { nParallel: null }), + // AFTER that clear, which both a first hydration and a model change trip: + // either would leave the control blank while the model runs on a remembered + // override, so the next Apply would save the blank over it. Adopted only + // when the running count matches, proving it is this model's own. + ...(seedLoadParams && + (slotsUnseeded || slotsModelChanged) && + rememberedNParallel != null && + rememberedNParallel === status.requested_parallel_slots && { + nParallel: rememberedNParallel, + }), // Re-seed on first hydration, model/variant changes, or a same-model backend // placement change. gpuStatusFields preserves dirty local edits in the last // case while advancing their loaded baselines. diff --git a/studio/frontend/src/features/chat/presets/preset-load-config.ts b/studio/frontend/src/features/chat/presets/preset-load-config.ts index 1083655cf2..c0a65c7886 100644 --- a/studio/frontend/src/features/chat/presets/preset-load-config.ts +++ b/studio/frontend/src/features/chat/presets/preset-load-config.ts @@ -12,6 +12,8 @@ import { DEFAULT_MAX_SEQ_LENGTH, KV_CACHE_DTYPES, MTP_SPECULATIVE_TYPES, + N_PARALLEL_MAX, + N_PARALLEL_MIN, SPECULATIVE_TYPES, normalizeMaxSeqLength, type PerModelConfig, @@ -30,6 +32,7 @@ export type PresetLoadConfig = Pick< | "kvCacheDtype" | "speculativeType" | "specDraftNMax" + | "nParallel" | "tensorParallel" | "gpuMemoryMode" | "gpuLayers" @@ -45,6 +48,7 @@ export const EMPTY_PRESET_LOAD_CONFIG: PresetLoadConfig = { kvCacheDtype: null, speculativeType: null, specDraftNMax: null, + nParallel: null, tensorParallel: false, }; @@ -107,6 +111,14 @@ export function normalizePresetLoadConfig( ? speculativeType : null, specDraftNMax, + nParallel: + typeof partial.nParallel === "number" && + Number.isFinite(partial.nParallel) + ? Math.max( + N_PARALLEL_MIN, + Math.min(N_PARALLEL_MAX, Math.round(partial.nParallel)), + ) + : null, tensorParallel: typeof partial.tensorParallel === "boolean" ? partial.tensorParallel @@ -151,6 +163,7 @@ export function capturePresetLoadConfig(): PresetLoadConfig | undefined { kvCacheDtype: snapshot.kvCacheDtype ?? null, speculativeType: normalizeSpeculativeType(snapshot.speculativeType), specDraftNMax: snapshot.specDraftNMax ?? null, + nParallel: snapshot.nParallel ?? null, tensorParallel: snapshot.tensorParallel ?? false, ...(snapshot.gpuMemoryMode === "manual" ? { gpuMemoryMode: "manual" as const } @@ -206,6 +219,7 @@ export function applyPresetLoadConfig( kvCacheDtype: config.kvCacheDtype ?? null, speculativeType: config.speculativeType ?? null, specDraftNMax: config.specDraftNMax ?? null, + nParallel: config.nParallel ?? null, tensorParallel: config.tensorParallel ?? false, chatTemplateOverride: null, gpuMemoryMode: config.gpuMemoryMode, @@ -231,6 +245,9 @@ export function formatPresetLoadConfigSummary( if (config.speculativeType && config.speculativeType !== "auto") { parts.push(`Spec ${config.speculativeType}`); } + if (config.nParallel != null) { + parts.push(`${config.nParallel} slots`); + } if (config.gpuMemoryMode === "manual") { parts.push("GPU manual"); } diff --git a/studio/frontend/src/features/chat/shared-composer.tsx b/studio/frontend/src/features/chat/shared-composer.tsx index 44436b92df..890dd022a0 100644 --- a/studio/frontend/src/features/chat/shared-composer.tsx +++ b/studio/frontend/src/features/chat/shared-composer.tsx @@ -1130,6 +1130,8 @@ export function SharedComposer({ ? { gpu_ids: effectiveSelectedGpuIds ?? undefined, gpu_memory_mode: effectiveGpuMemoryMode, + // Slots scale the KV estimate; keep validate sized like the load. + n_parallel: ownConfig.nParallel ?? null, } : {}), }); @@ -1198,6 +1200,7 @@ export function SharedComposer({ n_cpu_moe: effectiveNCpuMoe, tensor_split: compareLoadKnobs.splitRatio ?? undefined, gpu_ids: effectiveSelectedGpuIds ?? undefined, + n_parallel: ownConfig.nParallel ?? null, } : {}), }); @@ -1229,6 +1232,12 @@ export function SharedComposer({ effectiveCustomContextLength, ) : null; + // Slots this compare load committed. Diffusion ignores --parallel, so a + // count there would mint a phantom override a preset carries onto a GGUF. + const committedSlots = + targetIsGguf && !(resp.is_diffusion ?? false) + ? (ownConfig.nParallel ?? null) + : null; useChatRuntimeStore.setState({ supportsReasoning: resp.supports_reasoning ?? false, reasoningAlwaysOn: resp.reasoning_always_on ?? false, @@ -1237,6 +1246,9 @@ export function SharedComposer({ supportsTools: resp.supports_tools ?? false, kvCacheDtype: resp.cache_type_kv ?? null, loadedKvCacheDtype: resp.cache_type_kv ?? null, + // Click-time value, not the resolved echo (see the single-model load). + nParallel: committedSlots, + loadedNParallel: committedSlots, tensorParallel: resp.tensor_parallel ?? false, loadedTensorParallel: resp.tensor_parallel ?? false, defaultChatTemplate: resp.chat_template ?? null, diff --git a/studio/frontend/src/features/chat/stores/chat-runtime-store.ts b/studio/frontend/src/features/chat/stores/chat-runtime-store.ts index 98b8676c10..2984611780 100644 --- a/studio/frontend/src/features/chat/stores/chat-runtime-store.ts +++ b/studio/frontend/src/features/chat/stores/chat-runtime-store.ts @@ -968,6 +968,12 @@ type ChatRuntimeStore = { /** User --spec-draft-n-max override (null = platform default). */ specDraftNMax: number | null; loadedSpecDraftNMax: number | null; + /** User --parallel slots override for GGUF loads (null = server default). + * Never re-seeded from an echo: the resolved count would pin a blank control. */ + nParallel: number | null; + /** Slots the last successful load sent (null = default); the rollback + * re-sends it so a failed switch can't lose the override. */ + loadedNParallel: number | null; /** Tensor-parallel split (--split-mode tensor) toggle, GGUF multi-GPU only. */ tensorParallel: boolean; /** Backend-reported tensor-parallel state; null until first hydrated. */ @@ -1491,6 +1497,8 @@ export const useChatRuntimeStore = create((set, get) => ({ specFallbackReason: null, specDraftNMax: null, loadedSpecDraftNMax: null, + nParallel: null, + loadedNParallel: null, tensorParallel: false, loadedTensorParallel: null, gpuMemoryMode: readPersistedGpuMemoryMode(), @@ -1874,6 +1882,8 @@ export const useChatRuntimeStore = create((set, get) => ({ specFallbackReason: null, specDraftNMax: null, loadedSpecDraftNMax: null, + nParallel: null, + loadedNParallel: null, tensorParallel: false, loadedTensorParallel: null, // Standing preference: survives unload, unlike the per-model knobs above. diff --git a/studio/frontend/src/features/chat/types/api.ts b/studio/frontend/src/features/chat/types/api.ts index 3681b0f0cb..b67a9eda26 100644 --- a/studio/frontend/src/features/chat/types/api.ts +++ b/studio/frontend/src/features/chat/types/api.ts @@ -65,6 +65,11 @@ export interface LoadModelRequest { * when speculative_type resolves to "mtp" or "mtp+ngram". */ spec_draft_n_max?: number | null; + /** + * Parallel decode slots for llama-server (--parallel), 1..64. Omit/null = + * the launch default. The VRAM fitter may launch fewer to stay on GPU. + */ + n_parallel?: number | null; /** * Split the model across GPUs by tensor (--split-mode tensor) instead * of by layer for GGUF models. Multi-GPU only; no effect on a single GPU. @@ -202,6 +207,12 @@ export interface LoadModelResponse { gpu_ids?: number[] | null; /** User-requested GPU placement pool before fit-time narrowing. */ requested_gpu_ids?: number[] | null; + /** Slots the load was invoked with (else the --parallel default). Null for + * non-GGUF loads. */ + requested_parallel_slots?: number | null; + /** Slots llama-server actually runs, after any fit-time reduction. Null for + * non-GGUF loads. */ + parallel_slots?: number | null; } export interface UnloadModelRequest { @@ -263,6 +274,12 @@ export interface InferenceStatusResponse { gpu_ids?: number[] | null; /** User-requested GPU placement pool before fit-time narrowing. */ requested_gpu_ids?: number[] | null; + /** Slots the active load was invoked with (else the --parallel default). + * Null when no GGUF model is loaded. */ + requested_parallel_slots?: number | null; + /** Slots llama-server actually runs, after any fit-time reduction. Null when + * no GGUF model is loaded. */ + parallel_slots?: number | null; n_layers?: number | null; /** Model's MoE expert-layer count (the n_cpu_moe ceiling); 0 if not MoE. */ n_moe_layers?: number; diff --git a/studio/frontend/src/features/chat/utils/tool-status.ts b/studio/frontend/src/features/chat/utils/tool-status.ts new file mode 100644 index 0000000000..16c86bbd49 --- /dev/null +++ b/studio/frontend/src/features/chat/utils/tool-status.ts @@ -0,0 +1,15 @@ +// SPDX-License-Identifier: AGPL-3.0-only +// Copyright 2026-present the Unsloth AI Inc. team. All rights reserved. See /studio/LICENSE.AGPL-3.0 + +/** Mirrors NUDGE_TOOL_CALLS_STATUS in backend core/inference/tool_call_parser.py; keep in sync. */ +export const NUDGE_TOOL_CALLS_STATUS = "Nudging tool calls"; + +export type ToolStatusKind = "nudge" | "terminal" | "web"; + +/** Which glyph the badge shows: exact match for the nudge, "Running" prefix for sandbox tools, globe otherwise. */ +export function toolStatusKind(status: string): ToolStatusKind { + if (status === NUDGE_TOOL_CALLS_STATUS) { + return "nudge"; + } + return status.startsWith("Running") ? "terminal" : "web"; +} diff --git a/studio/frontend/src/features/model-picker/components/model-config-page.tsx b/studio/frontend/src/features/model-picker/components/model-config-page.tsx index 90202a2bcf..a753e9016e 100644 --- a/studio/frontend/src/features/model-picker/components/model-config-page.tsx +++ b/studio/frontend/src/features/model-picker/components/model-config-page.tsx @@ -46,6 +46,8 @@ import { MAX_SEQ_LENGTH_MIN, MAX_SEQ_LENGTH_STEP, MTP_SPECULATIVE_TYPES, + N_PARALLEL_MAX, + N_PARALLEL_MIN, type PerModelConfig, SPECULATIVE_TYPES, deletePerModelConfig, @@ -87,6 +89,7 @@ function hasNonDefaultAdvanced(config: PerModelConfig): boolean { config.kvCacheDtype != null || (config.speculativeType ?? "auto") !== "auto" || config.specDraftNMax != null || + config.nParallel != null || config.tensorParallel || config.chatTemplateOverride != null || (config.gpuMemoryMode ?? "auto") !== "auto" || @@ -541,6 +544,44 @@ function GgufAdvancedSettings({
)} +
+
+ Parallel Slots + + llama-server decode slots (--parallel) for concurrent requests. + Leave blank for the server default. More slots share the context + pool and use more VRAM; if they don't fit on GPU, fewer slots are + launched. + +
+ { + const raw = event.target.value; + if (raw === "") { + update({ nParallel: null }); + return; + } + const parsed = Number.parseInt(raw, 10); + if (Number.isFinite(parsed)) { + update({ + nParallel: Math.max( + N_PARALLEL_MIN, + Math.min(N_PARALLEL_MAX, parsed), + ), + }); + } + }} + aria-label="Parallel decode slots" + className={NUMBER_INPUT_CLASS} + /> +
+
Tensor Parallelism diff --git a/studio/frontend/src/features/model-picker/components/sidebar-model-config.tsx b/studio/frontend/src/features/model-picker/components/sidebar-model-config.tsx index 2d12c503a4..0d5f0fd663 100644 --- a/studio/frontend/src/features/model-picker/components/sidebar-model-config.tsx +++ b/studio/frontend/src/features/model-picker/components/sidebar-model-config.tsx @@ -43,6 +43,7 @@ function configSignature(config: PerModelConfig): string { config.kvCacheDtype ?? "", config.speculativeType ?? "", config.specDraftNMax ?? "", + config.nParallel ?? "", config.tensorParallel ? "1" : "0", config.chatTemplateOverride == null ? "" diff --git a/studio/frontend/src/features/model-picker/hooks/use-active-model-config.ts b/studio/frontend/src/features/model-picker/hooks/use-active-model-config.ts index 9d09ee6897..b0a6411019 100644 --- a/studio/frontend/src/features/model-picker/hooks/use-active-model-config.ts +++ b/studio/frontend/src/features/model-picker/hooks/use-active-model-config.ts @@ -20,6 +20,7 @@ export function useActiveModelConfig(): ActiveModelConfigState { const kvCacheDtype = useChatRuntimeStore((s) => s.kvCacheDtype); const speculativeType = useChatRuntimeStore((s) => s.speculativeType); const specDraftNMax = useChatRuntimeStore((s) => s.specDraftNMax); + const nParallel = useChatRuntimeStore((s) => s.nParallel); const tensorParallel = useChatRuntimeStore((s) => s.tensorParallel); const chatTemplateOverride = useChatRuntimeStore( (s) => s.chatTemplateOverride, @@ -44,6 +45,7 @@ export function useActiveModelConfig(): ActiveModelConfigState { kvCacheDtype: kvCacheDtype ?? null, speculativeType: speculativeType ?? "auto", specDraftNMax: specDraftNMax ?? null, + nParallel: nParallel ?? null, tensorParallel: tensorParallel ?? false, chatTemplateOverride: chatTemplateOverride ?? null, }; @@ -65,6 +67,7 @@ export function useActiveModelConfig(): ActiveModelConfigState { kvCacheDtype, speculativeType, specDraftNMax, + nParallel, tensorParallel, chatTemplateOverride, gpuMemoryMode, diff --git a/studio/frontend/src/features/model-picker/model-config/apply-per-model-config.ts b/studio/frontend/src/features/model-picker/model-config/apply-per-model-config.ts index c21d3e164a..829c522cb2 100644 --- a/studio/frontend/src/features/model-picker/model-config/apply-per-model-config.ts +++ b/studio/frontend/src/features/model-picker/model-config/apply-per-model-config.ts @@ -39,6 +39,7 @@ export function applyPerModelConfigToRuntime(config: PerModelConfig): void { normalizeSpeculativeType(config.speculativeType) ?? readPersistedSpeculativeType(), specDraftNMax: config.specDraftNMax ?? null, + nParallel: config.nParallel ?? null, tensorParallel: config.tensorParallel ?? false, chatTemplateOverride: cleanTemplate(config.chatTemplateOverride), // GPU Memory knobs are per-model (GGUF-only). Absent = defaults; the mode is @@ -77,6 +78,7 @@ export function currentRuntimePerModelConfig( kvCacheDtype: s.kvCacheDtype ?? null, speculativeType: normalizeSpeculativeType(s.speculativeType), specDraftNMax: s.specDraftNMax ?? null, + nParallel: s.nParallel ?? null, tensorParallel: s.tensorParallel ?? false, chatTemplateOverride: cleanTemplate(s.chatTemplateOverride), // Snapshot the live GPU knobs too so a failed switch rolls the previous @@ -101,6 +103,7 @@ export function perModelConfigsEqual( normalizeSpeculativeType(a.speculativeType) === normalizeSpeculativeType(b.speculativeType) && (a.specDraftNMax ?? null) === (b.specDraftNMax ?? null) && + (a.nParallel ?? null) === (b.nParallel ?? null) && Boolean(a.tensorParallel) === Boolean(b.tensorParallel) && cleanTemplate(a.chatTemplateOverride) === cleanTemplate(b.chatTemplateOverride) && diff --git a/studio/frontend/src/features/model-picker/model-config/per-model-config.ts b/studio/frontend/src/features/model-picker/model-config/per-model-config.ts index ba6d4cec99..196ac9e5a1 100644 --- a/studio/frontend/src/features/model-picker/model-config/per-model-config.ts +++ b/studio/frontend/src/features/model-picker/model-config/per-model-config.ts @@ -15,6 +15,7 @@ export interface PerModelConfig { kvCacheDtype: string | null; speculativeType: string | null; specDraftNMax: number | null; + nParallel: number | null; tensorParallel: boolean; chatTemplateOverride: string | null; // GPU Memory controls (per-model, GGUF-only), optional so older blobs still @@ -33,10 +34,16 @@ export const DEFAULT_PER_MODEL_CONFIG: PerModelConfig = { kvCacheDtype: null, speculativeType: null, specDraftNMax: null, + nParallel: null, tensorParallel: false, chatTemplateOverride: null, }; +// Mirrors llama_server_args.py PARALLEL_MIN/MAX (LoadRequest.n_parallel +// bounds). null = follow the server-wide default. +export const N_PARALLEL_MIN = 1; +export const N_PARALLEL_MAX = 64; + export const MAX_SEQ_LENGTH_MIN = 128; export const MAX_SEQ_LENGTH_MAX = 1048576; export const MAX_SEQ_LENGTH_STEP = 128; @@ -92,6 +99,7 @@ const STORED_CONFIG_FIELDS = new Set([ "kvCacheDtype", "speculativeType", "specDraftNMax", + "nParallel", "tensorParallel", "chatTemplateOverride", "gpuMemoryMode", @@ -292,6 +300,8 @@ function legacyEntryToConfig(raw: Record): PerModelConfig { typeof raw.speculativeType === "string" ? raw.speculativeType : null, specDraftNMax: typeof raw.specDraftNMax === "number" ? raw.specDraftNMax : null, + // Legacy blobs predate the parallel-slots knob. + nParallel: null, tensorParallel: typeof raw.tensorParallel === "boolean" ? raw.tensorParallel : false, chatTemplateOverride: null, @@ -459,6 +469,10 @@ function normalizeV1(partial: RawConfig): PerModelConfig { : null, speculativeType, specDraftNMax, + nParallel: + typeof partial.nParallel === "number" && Number.isFinite(partial.nParallel) + ? Math.max(N_PARALLEL_MIN, Math.min(N_PARALLEL_MAX, Math.round(partial.nParallel))) + : null, tensorParallel: typeof partial.tensorParallel === "boolean" ? partial.tensorParallel @@ -597,6 +611,7 @@ export function isDefaultConfig(config: PerModelConfig): boolean { (config.kvCacheDtype ?? null) === DEFAULT_PER_MODEL_CONFIG.kvCacheDtype && config.speculativeType === DEFAULT_PER_MODEL_CONFIG.speculativeType && config.specDraftNMax == null && + config.nParallel == null && Boolean(config.tensorParallel) === Boolean(DEFAULT_PER_MODEL_CONFIG.tensorParallel) && (config.chatTemplateOverride ?? null) === null && diff --git a/studio/frontend/tests/artifact-source-key.test.ts b/studio/frontend/tests/artifact-source-key.test.ts new file mode 100644 index 0000000000..e90037e603 --- /dev/null +++ b/studio/frontend/tests/artifact-source-key.test.ts @@ -0,0 +1,130 @@ +// SPDX-License-Identifier: AGPL-3.0-only +// Copyright 2026-present the Unsloth AI Inc. team. All rights reserved. See /studio/LICENSE.AGPL-3.0 + +import assert from "node:assert/strict"; +import { readFileSync } from "node:fs"; +import test from "node:test"; +import { fileURLToPath } from "node:url"; + +import ts from "typescript"; + +import { + buildArtifactSourceKey, + createArtifactId, + createChatArtifact, + hashArtifactCode, +} from "../src/features/chat/artifacts/types.ts"; + +// The shipped helper the component keys on, not a copy of it. +const sourceKey = buildArtifactSourceKey; + +const toolInput = (code: string) => ({ + code, + source: "tool" as const, + threadId: "thread-1", + sourceMessageId: "msg-1", + sourceToolCallId: "call_0", +}); + +const fenceInput = (code: string) => ({ + code, + source: "fence" as const, + threadId: "thread-1", + sourceMessageId: "msg-1", +}); + +test("tool artifact IDs are stable across code changes, so the ID alone is not enough", () => { + const first = createArtifactId(toolInput("

first

")); + const second = createArtifactId(toolInput("

second

")); + assert.equal(first, second); +}); + +test("the source key changes when a tool artifact's code changes", () => { + const first = createChatArtifact(toolInput("

first

")); + const second = createChatArtifact(toolInput("

second

")); + assert.notEqual(sourceKey(first), sourceKey(second)); +}); + +test("the source key changes when switching between fence artifacts", () => { + const first = createChatArtifact(fenceInput("

alpha

")); + const second = createChatArtifact(fenceInput("

bravo

")); + assert.notEqual(sourceKey(first), sourceKey(second)); +}); + +test("the source key is stable for an unchanged artifact, so no needless remount", () => { + const code = "

same

"; + assert.equal( + sourceKey(createChatArtifact(toolInput(code))), + sourceKey(createChatArtifact(toolInput(code))), + ); +}); + +// Equal line count, the shape where Streamdown's comparator sees no change. +test("the source key changes for two canvases with the same shape", () => { + const first = createChatArtifact( + toolInput("\n\n

Alpha

\n\n"), + ); + const second = createChatArtifact( + toolInput("\n\n

Bravo

\n\n"), + ); + assert.equal(first.code.length, second.code.length); + assert.equal(first.code.split("\n").length, second.code.split("\n").length); + assert.notEqual(sourceKey(first), sourceKey(second)); +}); + +test("hashArtifactCode separates same-length codes and empty from whitespace", () => { + assert.notEqual(hashArtifactCode("

ab

"), hashArtifactCode("

ba

")); + assert.notEqual(hashArtifactCode(""), hashArtifactCode(" ")); +}); + +const KEYED_BY_HELPER = /^\{buildArtifactSourceKey\(\s*artifact\s*\)\}$/; + +const SURFACE_PATH = fileURLToPath( + new URL( + "../src/features/chat/artifacts/artifact-surface.tsx", + import.meta.url, + ), +); + +/** The opening tag of `node`, for both `` and ``. */ +const openingTag = (node: ts.Node): ts.JsxOpeningLikeElement | null => { + if (ts.isJsxSelfClosingElement(node)) return node; + if (ts.isJsxElement(node)) return node.openingElement; + return null; +}; + +/** The `key` expression on the source view's Streamdown, or null if unkeyed. */ +function readStreamdownKey(): string | null { + const source = ts.createSourceFile( + SURFACE_PATH, + readFileSync(SURFACE_PATH, "utf8"), + ts.ScriptTarget.ESNext, + true, + ts.ScriptKind.TSX, + ); + let key: string | null = null; + const visit = (node: ts.Node): void => { + const opening = openingTag(node); + if (opening?.tagName.getText() === "Streamdown") { + for (const attribute of opening.attributes.properties) { + if ( + ts.isJsxAttribute(attribute) && + attribute.name.getText() === "key" + ) { + key = attribute.initializer?.getText() ?? ""; + } + } + } + node.forEachChild(visit); + }; + source.forEachChild(visit); + return key; +} + +// Without this the suite passes with the key deleted, which is the regression. +// No DOM renderer is available here, so assert the wiring in the source. +test("the source view's Streamdown is keyed by the shipped helper", () => { + const key = readStreamdownKey(); + assert.ok(key, "source view has no key prop"); + assert.match(key, KEYED_BY_HELPER); +}); diff --git a/studio/frontend/tests/tool-status.test.ts b/studio/frontend/tests/tool-status.test.ts new file mode 100644 index 0000000000..b20585bd08 --- /dev/null +++ b/studio/frontend/tests/tool-status.test.ts @@ -0,0 +1,45 @@ +// SPDX-License-Identifier: AGPL-3.0-only +// Copyright 2026-present the Unsloth AI Inc. team. All rights reserved. See /studio/LICENSE.AGPL-3.0 + +import assert from "node:assert/strict"; +import test from "node:test"; + +import { + NUDGE_TOOL_CALLS_STATUS, + toolStatusKind, +} from "../src/features/chat/utils/tool-status.ts"; + +test("the nudge status is the exact string the backend sends", () => { + // Mirrors tool_call_parser.py, so a reword on either side must break here. + assert.equal(NUDGE_TOOL_CALLS_STATUS, "Nudging tool calls"); + assert.equal(toolStatusKind(NUDGE_TOOL_CALLS_STATUS), "nudge"); +}); + +test("sandbox tools keep the terminal glyph", () => { + for (const status of [ + "Running Python: print(1)", + "Running Python...", + "Running: ls -la", + "Running command...", + ]) { + assert.equal(toolStatusKind(status), "terminal", status); + } +}); + +test("every other status keeps the globe", () => { + for (const status of [ + "Searching: red square", + "Reading: unsloth.ai", + "Reading page...", + "Searching documents: quarterly report", + "Calling: get_weather", + ]) { + assert.equal(toolStatusKind(status), "web", status); + } +}); + +test("a status that merely mentions nudging is not the nudge itself", () => { + // Exact match only: a tool named after the phrase must not steal the spinner. + assert.equal(toolStatusKind("Calling: Nudging tool calls"), "web"); + assert.equal(toolStatusKind("Nudging tool calls again"), "web"); +}); diff --git a/studio/install_python_stack.py b/studio/install_python_stack.py index 8c71d39e16..886abe218b 100644 --- a/studio/install_python_stack.py +++ b/studio/install_python_stack.py @@ -426,8 +426,8 @@ _GFX_TO_AMD_INDEX_ARCH: dict[str, str] = { } # bitsandbytes continuous-release_main wheels with the ROCm 4-bit GEMV fix -# (bnb PR #1887, post-0.49.2). bnb <= 0.49.2 NaNs at decode shape on every -# AMD GPU. Drop the pin once bnb 0.50+ ships on PyPI. +# (bnb #1887, post-0.49.2). bnb <= 0.49.2 NaNs at decode shape on every AMD GPU; +# PyPI 0.50.0 is the first release with the fix, so the fallback below is safe. _BNB_ROCM_PRERELEASE_URLS: dict[str, str] = { "x86_64": ( "https://github.com/bitsandbytes-foundation/bitsandbytes/releases/" @@ -448,7 +448,8 @@ _BNB_ROCM_PRERELEASE_URLS: dict[str, str] = { "bitsandbytes-1.33.7.preview-py3-none-win_amd64.whl" ), } -_BNB_ROCM_PYPI_FALLBACK = "bitsandbytes>=0.49.1" +# Keep in step with the amd extra in pyproject.toml and the install.sh fallback. +_BNB_ROCM_PYPI_FALLBACK = "bitsandbytes>=0.50.0" def _bnb_rocm_prerelease_url() -> str | None: @@ -460,6 +461,16 @@ def _bnb_rocm_prerelease_url() -> str | None: return _BNB_ROCM_PRERELEASE_URLS.get(arch) +def _bnb_rocm_arch_has_binary() -> bool: + """False on aarch64: bitsandbytes ships no ROCm kernels there at any version. + The PyPI 0.50.0 and continuous-release_main aarch64 wheels both carry only + libbitsandbytes_cpu.so plus CUDA variants, so neither install path gives + aarch64 a 4-bit backend and neither message may claim one. + """ + arch = platform.machine().lower() + return {"amd64": "x86_64", "arm64": "aarch64"}.get(arch, arch) != "aarch64" + + def _amd_smi_env() -> dict[str, str] | None: """On Windows, env with __COMPAT_LAYER=RunAsInvoker; None elsewhere. NB: RunAsInvoker doesn't stop amd-smi's runtime elevation (its manifest is @@ -1243,29 +1254,46 @@ _rocm_windows_torch_installed: bool = False def _install_bnb_windows_rocm() -> bool: - """Install the AMD Windows BNB prerelease wheel. Returns True on success. + """Install AMD Windows BNB, pre-release wheel first. Returns True on success. - The continuous-release wheel is intentionally mismatched: the filename - encodes 1.33.7.preview (parsed as 1.33.7rc0 by PEP 440) while the wheel - metadata reports 0.50.0.dev0. uv rejects this filename/metadata mismatch, - and bypassing it with UV_SKIP_WHEEL_FILENAME_CHECK still leaves uv mangling - the bitsandbytes install. Per the AMD install guide - (https://unsloth.ai/docs/get-started/install/amd/amd-hackathon) the wheel - must be installed with plain pip, not uv, so we force pip (force_pip=True); - plain pip performs no wheel filename/metadata check. + The wheel's filename version (1.33.7.preview, PEP 440 1.33.7rc0) does not + match its metadata (0.50.x.dev0). uv rejects the mismatch and still mangles + the install under UV_SKIP_WHEEL_FILENAME_CHECK, so force plain pip, which + performs no such check. Per the AMD install guide + (https://unsloth.ai/docs/get-started/install/amd/amd-hackathon). + + When that URL is blocked, fall back to PyPI. Its win_amd64 wheel ships + libbitsandbytes_rocm{714,72}.dll from 0.50.0 on, so the fallback is a real + ROCm build; before 0.50.0 it was CUDA-only, which is why there was none. """ _bnb_win_url = _BNB_ROCM_PRERELEASE_URLS.get("win_amd64") - if _bnb_win_url is None: - return False - _ok = pip_install_try( - "bitsandbytes (AMD Windows, pre-release main)", - "--force-reinstall", - "--no-cache-dir", - "--no-deps", - _bnb_win_url, - constrain = False, - force_pip = True, - ) + _ok = False + if _bnb_win_url is not None: + _ok = pip_install_try( + "bitsandbytes (AMD Windows, pre-release main)", + "--force-reinstall", + "--no-cache-dir", + "--no-deps", + _bnb_win_url, + constrain = False, + force_pip = True, + ) + if not _ok: + print( + _red( + " bnb pre-release install failed; falling back to PyPI " + f"{_BNB_ROCM_PYPI_FALLBACK}, which carries the ROCm 4-bit fix" + ) + ) + if not _ok: + _ok = pip_install_try( + "bitsandbytes (AMD Windows)", + "--force-reinstall", + "--no-cache-dir", + "--no-deps", + _BNB_ROCM_PYPI_FALLBACK, + constrain = False, + ) if not _ok: return False # Detect the actual ROCm DLL suffix in the wheel and set BNB_ROCM_VERSION so bnb @@ -1755,8 +1783,8 @@ def _ensure_rocm_torch() -> None: pass if _torch_ok: _rocm_windows_torch_installed = True - # ROCm torch is already installed, but the AMD Windows BNB wheel is still - # needed (the PyPI bitsandbytes ships only CUDA DLLs, fails on ROCm). + # ROCm torch is already installed, but bnb still needs the ROCm build + # (pre-release wheel, else PyPI >=0.50.0). _install_bnb_windows_rocm() return # torch was wiped between runs; fall through to the full install path @@ -1834,12 +1862,12 @@ def _ensure_rocm_torch() -> None: # separate dependency -- a BNB install failure must NOT roll back the # torch ROCm install. _rocm_windows_torch_installed = True - # Always install AMD Windows bitsandbytes -- the PyPI wheel ships only - # CUDA DLLs and fails on ROCm. Install even when torch was already a - # ROCm build so `studio update` repairs a broken bnb. + # Always install AMD Windows bitsandbytes, even when torch was already a + # ROCm build, so `studio update` repairs a broken bnb. if not _install_bnb_windows_rocm(): print( - " Warning: AMD Windows bitsandbytes install failed; " + " Warning: AMD Windows bitsandbytes install failed " + "(pre-release and PyPI); " "ROCm torch is installed but bitsandbytes may need manual install" ) return @@ -2170,10 +2198,13 @@ def _ensure_rocm_torch() -> None: force_pip = True, ) if not _bnb_installed: + _fallback_note = ( + ", which carries the ROCm 4-bit fix" if _bnb_rocm_arch_has_binary() else "" + ) print( _red( " bnb pre-release install failed; falling back to PyPI " - "(4-bit decode will be broken on ROCm)" + f"{_BNB_ROCM_PYPI_FALLBACK}{_fallback_note}" ) ) if not _bnb_installed: @@ -2185,6 +2216,14 @@ def _ensure_rocm_torch() -> None: _BNB_ROCM_PYPI_FALLBACK, constrain = False, ) + if not _bnb_rocm_arch_has_binary(): + print( + _red( + " aarch64: bitsandbytes ships no ROCm kernels on this arch; " + "4-bit QLoRA needs a source build -- " + "https://docs.unsloth.ai/get-started/install-and-update/amd" + ) + ) # _uv_safe_path is imported from backend.utils.uv_path_safety (shared with mlx_repair). @@ -2853,6 +2892,30 @@ def patch_package_file(package_name: str, relative_path: str, url: str) -> None: # -- Main install sequence --------------------------------------------- +def _has_working_git() -> bool: + """Match install.sh's _has_working_git: on PATH *and* actually runnable. + + A present-but-broken git (a bare xcrun shim) counts as missing there too. Testing + only shutil.which disagreed, so the installer promised to skip the git+https triton + requirement and then tried to fetch it anyway. + """ + exe = shutil.which("git") + if exe is None: + return False + try: + return ( + subprocess.run( + [exe, "--version"], + stdout = subprocess.DEVNULL, + stderr = subprocess.DEVNULL, + timeout = 30, + ).returncode + == 0 + ) + except (OSError, subprocess.SubprocessError): + return False + + def install_python_stack() -> int: global USE_UV, _STEP, _TOTAL _STEP = 0 @@ -3158,17 +3221,22 @@ def install_python_stack() -> int: _torchao_spec, ) - # 5. Triton kernels (no-deps, from source). Skip on Windows and macOS - # (no support). + # 5. Triton kernels (no-deps, from source). Skipped on Windows/macOS (no support) + # and without git (the requirement is a git+https URL); a training speedup + # only, so warn rather than fail the install. if not IS_WINDOWS and not IS_MACOS: - _progress("triton kernels") - pip_install( - "Installing triton kernels", - "--no-deps", - "--no-cache-dir", - req = REQ_ROOT / "triton-kernels.txt", - constrain = False, - ) + if not _has_working_git(): + _progress("triton kernels (skipped, no git)") + _safe_print(" no working git -- skipping triton kernels (training speedup only)") + else: + _progress("triton kernels") + pip_install( + "Installing triton kernels", + "--no-deps", + "--no-cache-dir", + req = REQ_ROOT / "triton-kernels.txt", + constrain = False, + ) if not IS_WINDOWS and not IS_MACOS and not NO_TORCH: _progress("flash-attn") diff --git a/studio/setup.ps1 b/studio/setup.ps1 index 0734b9c2fa..a4eb54a9ef 100644 --- a/studio/setup.ps1 +++ b/studio/setup.ps1 @@ -3122,7 +3122,7 @@ sys.exit(0 if install_manifest.remove_manifest() else 1) if (-not $_ManifestDropped) { Write-Host "[ERROR] Could not remove the stale unsloth_install_manifest.json." -ForegroundColor Red Write-Host " Refusing to install behind a marker that still reports this venv as complete." -ForegroundColor Red - exit 1 + Exit-SetupFailure "Could not remove the stale unsloth_install_manifest.json" } if ($script:UnslothVerbose) { diff --git a/studio/src-tauri/src/install.rs b/studio/src-tauri/src/install.rs index d7226bf901..39d67dc427 100644 --- a/studio/src-tauri/src/install.rs +++ b/studio/src-tauri/src/install.rs @@ -783,6 +783,14 @@ pub fn record_install_intentional_stop(state: &InstallState, diagnostics: &Diagn } } +/// True while an installer runs; quitting now would leave a broken venv. +pub fn is_install_running(state: &InstallState) -> bool { + state + .lock() + .map(|install| install.child.is_some()) + .unwrap_or(false) +} + /// Stop a running install process gracefully. /// Unix: SIGTERM to process group -> wait up to 5s -> SIGKILL /// Windows: hidden taskkill /T /F to terminate the installer tree diff --git a/studio/src-tauri/src/main.rs b/studio/src-tauri/src/main.rs index a867700035..0d39217ecd 100644 --- a/studio/src-tauri/src/main.rs +++ b/studio/src-tauri/src/main.rs @@ -85,6 +85,33 @@ fn setup_custom_titlebar(app: &tauri::App) -> Result<(), Box bool { + use tauri_plugin_dialog::{DialogExt, MessageDialogButtons, MessageDialogKind}; + + let Some(install_state) = app.try_state::() else { + return true; + }; + if !install::is_install_running(&install_state) { + return true; + } + app.dialog() + .message( + "Unsloth Studio is still installing. Quitting now stops it part-way and \ + leaves the installation incomplete, so it will need to be repaired before \ + it can start.", + ) + .kind(MessageDialogKind::Warning) + .title("Installation in progress") + .buttons(MessageDialogButtons::OkCancelCustom( + "Quit anyway".to_string(), + "Keep installing".to_string(), + )) + .blocking_show() +} + fn cleanup_child_processes(app: &tauri::AppHandle) { let diagnostics_state = app .try_state::() @@ -138,6 +165,9 @@ fn setup_tray(app: &tauri::App) -> Result<(), Box> { // leaving the backend orphaned. let app_handle = app.clone(); std::thread::spawn(move || { + if !confirm_quit_during_install(&app_handle) { + return; + } cleanup_child_processes(&app_handle); app_handle.exit(0); }); diff --git a/tests/conftest.py b/tests/conftest.py index 3478a19af8..aaeeb840ce 100644 --- a/tests/conftest.py +++ b/tests/conftest.py @@ -123,7 +123,34 @@ def _install_device_type_stub(name: str) -> None: sys.modules[name] = stub +def _preimport_bitsandbytes() -> None: + """Bind bitsandbytes against the real torch before the CUDA spoof below. + + `bitsandbytes/__init__.py` runs `if torch.cuda.is_available(): from .backends.cuda + import ops`, and that module reads `torch._C._cuda_getCurrentRawStream`, which a + CPU-only torch build does not expose. `_preload_device_type` patches + `torch.cuda.is_available` to return True, so a bitsandbytes import landing inside + that window takes the CUDA branch and dies with AttributeError. + + Python then drops `bitsandbytes` from sys.modules but leaves `bitsandbytes.functional` + and the rest of its submodules cached, so the next import re-executes __init__ against + those cached submodules, re-binds nothing, and hands back a module with no + `.functional`. `unsloth/kernels/utils.py` reads `bnb.functional.get_ptr` at module + scope, so every later `import unsloth` in that process dies with + "module 'bitsandbytes' has no attribute 'functional'". + + Importing first, outside the window, keeps bitsandbytes on its CPU backend and fully + usable. Must stay ahead of the `_preload_device_type` calls below. + """ + try: + import bitsandbytes # noqa: F401 + except Exception: + # A genuinely absent or broken wheel is unsloth's own degradation path. + pass + + if not _has_real_accelerator(): + _preimport_bitsandbytes() if not _preload_device_type("unsloth_zoo", prereqs = ("utils",)): _install_device_type_stub("unsloth_zoo.device_type") if not _preload_device_type("unsloth"): diff --git a/tests/python/test_conftest_bitsandbytes_preimport.py b/tests/python/test_conftest_bitsandbytes_preimport.py new file mode 100644 index 0000000000..8ed80d6232 --- /dev/null +++ b/tests/python/test_conftest_bitsandbytes_preimport.py @@ -0,0 +1,85 @@ +# SPDX-License-Identifier: AGPL-3.0-only +# Copyright 2026-present the Unsloth AI Inc. team. All rights reserved. + +"""Guard the ordering that keeps bitsandbytes usable under the GPU-free harness. + +tests/conftest.py patches `torch.cuda.is_available` to return True so +`device_type.py`'s @cache captures "cuda" on a GPU-less runner. bitsandbytes reads +that same flag at import time to decide whether to import its CUDA backend, and that +backend touches `torch._C._cuda_getCurrentRawStream`, absent from CPU-only torch +builds. A bitsandbytes import landing inside the spoof window therefore raises, and +the failure is not recoverable within the process: Python drops `bitsandbytes` from +sys.modules while leaving its submodules cached, so every later import returns a +module with no `.functional`, and `unsloth/kernels/utils.py` dies at module scope. + +Clearing sys.modules is not a way out either -- re-executing `bitsandbytes._ops` +raises "Tried to register an operator ... multiple times". The import simply must not +fail, which is what `_preimport_bitsandbytes()` guarantees by running first. + +Source-level rather than behavioural on purpose: the failure needs a CPU-only torch +build to reproduce, so a runtime assertion would pass vacuously wherever CUDA torch +is installed, which is most developer machines. +""" + +from __future__ import annotations + +import ast +from pathlib import Path + +CONFTEST = Path(__file__).resolve().parents[1] / "conftest.py" + + +def _accelerator_guard_body(tree: ast.Module) -> list[ast.stmt]: + for node in tree.body: + if isinstance(node, ast.If) and "_has_real_accelerator" in ast.dump(node.test): + return node.body + raise AssertionError("tests/conftest.py has no `if not _has_real_accelerator():` block") + + +def _called_names(body: list[ast.stmt]) -> list[str]: + names = [] + for stmt in body: + for node in ast.walk(stmt): + if isinstance(node, ast.Call) and isinstance(node.func, ast.Name): + names.append(node.func.id) + return names + + +def test_conftest_defines_the_bitsandbytes_preimport(): + tree = ast.parse(CONFTEST.read_text(encoding = "utf-8")) + defined = {n.name for n in tree.body if isinstance(n, ast.FunctionDef)} + assert "_preimport_bitsandbytes" in defined, ( + "tests/conftest.py must define _preimport_bitsandbytes(); without it a " + "bitsandbytes import inside the CUDA spoof window permanently breaks " + "`import unsloth` for the rest of the process" + ) + + +def test_bitsandbytes_is_preimported_before_the_cuda_spoof(): + tree = ast.parse(CONFTEST.read_text(encoding = "utf-8")) + called = _called_names(_accelerator_guard_body(tree)) + + assert "_preimport_bitsandbytes" in called, ( + "_preimport_bitsandbytes() is never called inside the " + "`if not _has_real_accelerator():` block" + ) + assert "_preload_device_type" in called, "conftest no longer calls _preload_device_type" + assert called.index("_preimport_bitsandbytes") < called.index("_preload_device_type"), ( + "_preimport_bitsandbytes() must run BEFORE _preload_device_type(), which is what " + "patches torch.cuda.is_available; importing bitsandbytes inside that window makes " + "it take its CUDA backend on a CPU-only torch and poisons sys.modules" + ) + + +def test_preimport_swallows_a_genuinely_missing_wheel(): + """An absent bitsandbytes stays unsloth's own degradation path, not a collection error.""" + tree = ast.parse(CONFTEST.read_text(encoding = "utf-8")) + fn = next( + n + for n in tree.body + if isinstance(n, ast.FunctionDef) and n.name == "_preimport_bitsandbytes" + ) + assert any(isinstance(node, ast.Try) for node in ast.walk(fn)), ( + "_preimport_bitsandbytes() must guard its import with try/except so a missing or " + "broken wheel does not turn into a collection error" + ) diff --git a/tests/python/test_cross_platform_parity.py b/tests/python/test_cross_platform_parity.py index 6c2a1d09cf..b20e715ebc 100644 --- a/tests/python/test_cross_platform_parity.py +++ b/tests/python/test_cross_platform_parity.py @@ -862,3 +862,76 @@ class TestNoTorchPersistenceParity: manifest = (REPO_ROOT / "studio" / "install_manifest.py").read_text(encoding = "utf-8") assert 'NO_TORCH_TRUTHY: Tuple[str, ...] = ("1", "true", "yes", "on")' in manifest assert "install_manifest.NO_TORCH_TRUTHY" in STACK_PY.read_text(encoding = "utf-8") + + +class TestAmdBnbFloorParity: + """bitsandbytes <= 0.49.2 NaNs at 4-bit decode shape on every AMD GPU; the ROCm + 4-bit GEMV fix (bnb #1887) first ships on PyPI in 0.50.0. The `amd` extra, + install.sh and the Studio stack resolve bitsandbytes independently, so all three + must carry the same floor or an unreachable pre-release wheel silently reinstates + the broken range.""" + + FLOOR = "0.50.0" + PYPROJECT = REPO_ROOT / "pyproject.toml" + + def test_amd_extra_floor(self): + text = self.PYPROJECT.read_text(encoding = "utf-8") + amd = re.search(r"^amd = \[(.*?)^\]", text, re.S | re.M) + assert amd, "pyproject.toml must define an `amd` extra" + specs = re.findall(r'"(bitsandbytes[^"]*)"', amd.group(1)) + assert specs, "the amd extra must pin bitsandbytes" + for spec in specs: + assert spec.startswith( + f"bitsandbytes>={self.FLOOR}" + ), f"amd extra bitsandbytes floor must be >={self.FLOOR}, got {spec!r}" + + def test_install_sh_pypi_fallback_floor(self): + text = INSTALL_SH.read_text(encoding = "utf-8") + assert ( + f'_BNB_ROCM_PYPI_FALLBACK="bitsandbytes>={self.FLOOR}"' in text + ), f"install.sh _install_bnb_rocm PyPI fallback must floor at {self.FLOOR}" + + def test_stack_py_pypi_fallback_floor(self): + text = STACK_PY.read_text(encoding = "utf-8") + assert ( + f'_BNB_ROCM_PYPI_FALLBACK = "bitsandbytes>={self.FLOOR}"' in text + ), f"install_python_stack.py PyPI fallback must floor at {self.FLOOR}" + + def test_no_installer_still_allows_the_broken_range(self): + for path in (INSTALL_SH, INSTALL_PS1, SETUP_PS1, STACK_PY, self.PYPROJECT): + text = path.read_text(encoding = "utf-8") + for line in text.splitlines(): + if "bitsandbytes>=0.49" in line and not line.lstrip().startswith(("#", "//")): + raise AssertionError( + f"{path.name} still floors bitsandbytes in the broken ROCm range: {line.strip()!r}" + ) + + def test_fallback_is_not_reported_as_broken(self): + """The fallback now installs the first fixed release, so neither installer + may still call 4-bit decode broken on ROCm.""" + for path in (INSTALL_SH, STACK_PY): + text = path.read_text(encoding = "utf-8") + assert ( + "4-bit decode broken on ROCm" not in text + ), f"{path.name} still reports the repaired PyPI fallback as broken" + assert ( + "4-bit decode will be broken on ROCm" not in text + ), f"{path.name} still reports the repaired PyPI fallback as broken" + + def test_aarch64_is_not_told_it_has_a_rocm_backend(self): + """bitsandbytes ships no ROCm kernels in its aarch64 wheel at any version, so + neither installer may hand aarch64 the x86_64 "carries the ROCm 4-bit fix" + message, and both must warn that 4-bit needs a source build there.""" + sh = INSTALL_SH.read_text(encoding = "utf-8") + assert "_bnb_rocm_arch_has_binary()" in sh + assert "_warn_bnb_no_rocm_binary()" in sh + assert ( + sh.count("_warn_bnb_no_rocm_binary\n") >= 2 + ), "install.sh must warn on aarch64 after both the pre-release and the fallback install" + py = STACK_PY.read_text(encoding = "utf-8") + assert "def _bnb_rocm_arch_has_binary(" in py + assert "_bnb_rocm_arch_has_binary()" in py + for text, name in ((sh, "install.sh"), (py, "install_python_stack.py")): + assert ( + "4-bit QLoRA needs a source build" in text + ), f"{name} must tell aarch64 users 4-bit needs a source build" diff --git a/tests/saving/language_models/test_merge_model_perplexity_llama-3.2.py b/tests/saving/language_models/test_merge_model_perplexity_llama-3.2.py index 3b75a13756..a549e58562 100644 --- a/tests/saving/language_models/test_merge_model_perplexity_llama-3.2.py +++ b/tests/saving/language_models/test_merge_model_perplexity_llama-3.2.py @@ -96,12 +96,11 @@ def load_and_compute_8bit_ppl( if __name__ == "__main__": mp.set_start_method("spawn", force = True) - if torch.cuda.is_bf16_supported(): - compute_dtype = torch.bfloat16 - attn_implementation = "flash_attention_2" - else: - compute_dtype = torch.float16 - attn_implementation = "sdpa" + from unsloth import is_bfloat16_supported + from unsloth.models._utils import HAS_FLASH_ATTENTION + + compute_dtype = torch.bfloat16 if is_bfloat16_supported() else torch.float16 + attn_implementation = "flash_attention_2" if HAS_FLASH_ATTENTION else "sdpa" model, tokenizer = FastLanguageModel.from_pretrained( model_name = "unsloth/Llama-3.2-3B-Instruct", diff --git a/tests/saving/language_models/test_merge_model_perplexity_mistral.py b/tests/saving/language_models/test_merge_model_perplexity_mistral.py index 8cc833c2b1..50b0d3caf4 100644 --- a/tests/saving/language_models/test_merge_model_perplexity_mistral.py +++ b/tests/saving/language_models/test_merge_model_perplexity_mistral.py @@ -121,12 +121,11 @@ def load_and_compute_8bit_ppl( if __name__ == "__main__": mp.set_start_method("spawn", force = True) - if torch.cuda.is_bf16_supported(): - compute_dtype = torch.bfloat16 - attn_implementation = "flash_attention_2" - else: - compute_dtype = torch.float16 - attn_implementation = "sdpa" + from unsloth import is_bfloat16_supported + from unsloth.models._utils import HAS_FLASH_ATTENTION + + compute_dtype = torch.bfloat16 if is_bfloat16_supported() else torch.float16 + attn_implementation = "flash_attention_2" if HAS_FLASH_ATTENTION else "sdpa" model, tokenizer = FastLanguageModel.from_pretrained( model_name = "unsloth/mistral-7b-v0.3", diff --git a/tests/saving/language_models/test_merge_model_perplexity_phi_4.py b/tests/saving/language_models/test_merge_model_perplexity_phi_4.py index 6f79bfdb71..9c7f6c77af 100644 --- a/tests/saving/language_models/test_merge_model_perplexity_phi_4.py +++ b/tests/saving/language_models/test_merge_model_perplexity_phi_4.py @@ -98,12 +98,11 @@ def load_and_compute_8bit_ppl( if __name__ == "__main__": mp.set_start_method("spawn", force = True) - if torch.cuda.is_bf16_supported(): - compute_dtype = torch.bfloat16 - attn_implementation = "flash_attention_2" - else: - compute_dtype = torch.float16 - attn_implementation = "sdpa" + from unsloth import is_bfloat16_supported + from unsloth.models._utils import HAS_FLASH_ATTENTION + + compute_dtype = torch.bfloat16 if is_bfloat16_supported() else torch.float16 + attn_implementation = "flash_attention_2" if HAS_FLASH_ATTENTION else "sdpa" model, tokenizer = FastLanguageModel.from_pretrained( model_name = "unsloth/Phi-4", diff --git a/tests/saving/language_models/test_merged_model_perplexity_llama-3.1-8b.py b/tests/saving/language_models/test_merged_model_perplexity_llama-3.1-8b.py index c07b37024f..dcbaad13e1 100644 --- a/tests/saving/language_models/test_merged_model_perplexity_llama-3.1-8b.py +++ b/tests/saving/language_models/test_merged_model_perplexity_llama-3.1-8b.py @@ -95,12 +95,11 @@ def load_and_compute_8bit_ppl( if __name__ == "__main__": mp.set_start_method("spawn", force = True) - if torch.cuda.is_bf16_supported(): - compute_dtype = torch.bfloat16 - attn_implementation = "flash_attention_2" - else: - compute_dtype = torch.float16 - attn_implementation = "sdpa" + from unsloth import is_bfloat16_supported + from unsloth.models._utils import HAS_FLASH_ATTENTION + + compute_dtype = torch.bfloat16 if is_bfloat16_supported() else torch.float16 + attn_implementation = "flash_attention_2" if HAS_FLASH_ATTENTION else "sdpa" model, tokenizer = FastLanguageModel.from_pretrained( model_name = "unsloth/Llama-3.1-8B-Instruct", diff --git a/tests/saving/language_models/test_merged_model_perplexity_qwen_2.5.py b/tests/saving/language_models/test_merged_model_perplexity_qwen_2.5.py index cb444d1591..cfa364c697 100644 --- a/tests/saving/language_models/test_merged_model_perplexity_qwen_2.5.py +++ b/tests/saving/language_models/test_merged_model_perplexity_qwen_2.5.py @@ -164,12 +164,11 @@ def load_and_compute_8bit_ppl( if __name__ == "__main__": mp.set_start_method("spawn", force = True) - if torch.cuda.is_bf16_supported(): - compute_dtype = torch.bfloat16 - attn_implementation = "flash_attention_2" - else: - compute_dtype = torch.float16 - attn_implementation = "sdpa" + from unsloth import is_bfloat16_supported + from unsloth.models._utils import HAS_FLASH_ATTENTION + + compute_dtype = torch.bfloat16 if is_bfloat16_supported() else torch.float16 + attn_implementation = "flash_attention_2" if HAS_FLASH_ATTENTION else "sdpa" model, tokenizer = FastLanguageModel.from_pretrained( model_name = "unsloth/Qwen2.5-7B-Instruct", @@ -210,8 +209,6 @@ if __name__ == "__main__": loftq_config = None, ) - from unsloth import is_bfloat16_supported - trainer = SFTTrainer( model = model, tokenizer = tokenizer, diff --git a/tests/sh/test_linux_deps_gate.sh b/tests/sh/test_linux_deps_gate.sh new file mode 100755 index 0000000000..db25c5eb80 --- /dev/null +++ b/tests/sh/test_linux_deps_gate.sh @@ -0,0 +1,210 @@ +#!/bin/bash +# SPDX-License-Identifier: AGPL-3.0-only +# Copyright 2026-present the Unsloth AI Inc. team. All rights reserved. See /studio/LICENSE.AGPL-3.0 +# +# Guards the Linux/WSL system-dependency gate in install.sh. +# +# History: the gate hard-required cmake, git, gcc and libcurl4-openssl-dev, installing +# them on apt distros and `exit 1`-ing everywhere else. Nothing on the consumer path +# builds anything, so it stranded every non-apt distro over unused tooling. +# +# The contract now: only a download transport (curl or wget) is fatal, build tooling +# is a warning, and git is required for --local only (unsloth-zoo git+https URL). +set -e + +SCRIPT_DIR="$(cd "$(dirname "$0")" && pwd)" +INSTALL_SH="$SCRIPT_DIR/../../install.sh" +PASS=0 +FAIL=0 + +assert_contains() { + _label="$1"; _haystack="$2"; _needle="$3" + if echo "$_haystack" | grep -qF "$_needle"; then + echo " PASS: $_label" + PASS=$((PASS + 1)) + else + echo " FAIL: $_label (expected to find '$_needle')" + echo " ---- output ----"; echo "$_haystack" | sed 's/^/ | /' + FAIL=$((FAIL + 1)) + fi +} + +assert_not_contains() { + _label="$1"; _haystack="$2"; _needle="$3" + if echo "$_haystack" | grep -qF "$_needle"; then + echo " FAIL: $_label (found '$_needle' but should not)" + FAIL=$((FAIL + 1)) + else + echo " PASS: $_label" + PASS=$((PASS + 1)) + fi +} + +# ── Extract the functions under test ── +_FN_FILE=$(mktemp) +sed -n '/^_has_working_git()/,/^}/p' "$INSTALL_SH" > "$_FN_FILE" +sed -n '/^_check_linux_deps()/,/^}/p' "$INSTALL_SH" >> "$_FN_FILE" + +if ! grep -q '_check_linux_deps()' "$_FN_FILE"; then + echo "FAIL: could not extract _check_linux_deps from install.sh" + echo " (the gate must stay a top-level function so this test can reach it)" + exit 1 +fi + +_HARNESS=$(mktemp) +cat > "$_HARNESS" <<'HARNESS' +C_WARN=''; C_ERR=''; C_OK=''; C_DIM=''; C_RST='' +step() { echo "STEP $1 $2"; } +substep() { echo "SUBSTEP $1"; } +tauri_log() { echo "[TAURI:$1] $2"; } +# Records its args so a test can tell "asked apt for curl" from "asked for everything". +_smart_apt_install() { echo "APT_CALLED: $*"; } +HARNESS + +_BIN=$(mktemp -d) +_mk() { printf '#!/bin/sh\n%s\n' "$2" > "$_BIN/$1"; chmod +x "$_BIN/$1"; } + +# PATH is the sandbox and ONLY the sandbox, so unstocked tools are genuinely absent and +# the host's /usr/bin/cmake cannot leak in. bash must therefore be invoked absolutely. +_SH="${BASH:-/bin/bash}" + +_run_gate() { + # $1 = STUDIO_LOCAL_INSTALL + ( PATH="$_BIN"; export PATH + "$_SH" -c ". '$_HARNESS'; . '$_FN_FILE'; STUDIO_LOCAL_INSTALL=$1; _check_linux_deps; echo \"RC=\$?\"" 2>&1 ) +} + +echo "=== Fedora/Arch/openSUSE shape: curl present, no build tooling, no apt ===" +# Used to exit 1 with "supported on apt-based Linux distributions only". +rm -f "$_BIN"/* +_mk curl 'exit 0' +_out="$(_run_gate false)" +assert_contains "install proceeds" "$_out" "RC=0" +assert_contains "says the prebuilt is used" "$_out" "using prebuilt llama.cpp" +assert_contains "names what is missing" "$_out" "cmake" +assert_contains "says it is not required" "$_out" "Not required" +assert_not_contains "does not demand a package manager" "$_out" "apt-based" +assert_not_contains "does not reach apt for build tools" "$_out" "APT_CALLED" + +echo "=== wget instead of curl is an acceptable transport ===" +rm -f "$_BIN"/* +_mk wget 'exit 0' +_out="$(_run_gate false)" +assert_contains "install proceeds" "$_out" "RC=0" +assert_not_contains "does not ask apt for curl" "$_out" "APT_CALLED" + +echo "=== no transport at all, no apt: the one genuinely fatal case ===" +rm -f "$_BIN"/* +_out="$(_run_gate false)" +assert_contains "fails" "$_out" "RC=1" +assert_contains "names the missing transport" "$_out" "curl" +assert_contains "explains what it is needed for" "$_out" "download" +assert_contains "gives a non-apt remedy" "$_out" "dnf install curl" + +echo "=== no transport, apt available: auto-install curl and ONLY curl ===" +rm -f "$_BIN"/* +_mk apt-get 'exit 0' +_out="$(_run_gate false)" +assert_contains "install proceeds" "$_out" "RC=0" +assert_contains "asks apt for curl" "$_out" "APT_CALLED: curl" +assert_not_contains "does not ask apt for cmake" "$_out" "APT_CALLED: curl cmake" +# Build tooling still appears in the warning line, so match the apt call, not names. +assert_contains "apt asked for exactly curl" "$_out" "APT_CALLED: curl +" +assert_contains "build tooling only warned about" "$_out" "using prebuilt llama.cpp" + +echo "=== fully equipped machine: no warnings ===" +rm -f "$_BIN"/* +for t in curl cmake gcc curl-config git; do _mk "$t" 'exit 0'; done +_out="$(_run_gate false)" +assert_contains "install proceeds" "$_out" "RC=0" +assert_contains "reports everything found" "$_out" "all system dependencies found" +assert_not_contains "no prebuilt fallback warning" "$_out" "using prebuilt llama.cpp" + +echo "=== apt present: git is auto-installed, because triton_kernels needs it ===" +# Regression: making git optional without this failed at "6/14 triton kernels", whose +# requirement is a git+https URL. +rm -f "$_BIN"/* +_mk curl 'exit 0' +_mk apt-get 'exit 0' +_out="$(_run_gate false)" +assert_contains "install proceeds" "$_out" "RC=0" +assert_contains "apt is asked for git" "$_out" "git" +assert_contains "apt is actually called" "$_out" "APT_CALLED" + +echo "=== no apt and no git: warn about the triton skip, do not fail ===" +rm -f "$_BIN"/* +_mk curl 'exit 0' +_out="$(_run_gate false)" +assert_contains "install proceeds" "$_out" "RC=0" +assert_contains "names the consequence of no git" "$_out" "triton kernels" +assert_not_contains "does not call it required to run" "$_out" "is required" + +echo "=== --local without git: must fail loudly (matches macOS) ===" +rm -f "$_BIN"/* +_mk curl 'exit 0' +_out="$(_run_gate true)" +assert_contains "fails" "$_out" "RC=1" +assert_contains "explains why git is needed" "$_out" "unsloth-zoo" +assert_contains "says a normal install needs none" "$_out" "non---local" + +echo "=== --local with a git that exists but does not work ===" +# Mirrors the macOS CLT-stub shape: `command -v git` succeeds, running it fails. +rm -f "$_BIN"/* +_mk curl 'exit 0' +_mk git 'echo "broken" >&2; exit 1' +_out="$(_run_gate true)" +assert_contains "still fails" "$_out" "RC=1" + +echo "=== --local with a working git proceeds ===" +rm -f "$_BIN"/* +_mk curl 'exit 0' +_mk git 'exit 0' +_out="$(_run_gate true)" +assert_contains "install proceeds" "$_out" "RC=0" + +echo "=== optional apt packages never ask for elevation, in any mode ===" +# Regression: the optional bypass sat inside the TAURI_MODE branch, so a plain +# `curl | sh` on a non-root Debian box still hit the sudo prompt (default yes) and +# installed cmake, GCC and dev headers that nothing on the consumer path uses. +_APT_FN=$(mktemp) +{ + sed -n '/^_is_pkg_installed()/,/^}$/p' "$INSTALL_SH" + sed -n '/^_apt_distro_description()/,/^}$/p' "$INSTALL_SH" + sed -n '/^_can_read_tty()/,/^}$/p' "$INSTALL_SH" + sed -n '/^_smart_apt_install()/,/^}$/p' "$INSTALL_SH" +} > "$_APT_FN" + +_run_apt() { + # $1 = TAURI_MODE, $2 = _SMART_APT_OPTIONAL. apt-get always fails, as it does + # for a non-root user, so the function reaches its escalation decision. + rm -f "$_BIN"/* + _mk apt-get 'exit 100' + _mk sudo 'echo "ELEVATION_ATTEMPTED: $*"; exit 1' + ln -sf "$(command -v sed)" "$_BIN/sed" # the function trims its list with sed + # _APT_FN after _HARNESS so the real function replaces the recording stub. + ( PATH="$_BIN"; export PATH + "$_SH" -c ". '$_HARNESS'; . '$_APT_FN'; TAURI_MODE=$1; _SMART_APT_OPTIONAL=$2 + ( _smart_apt_install unsloth_absent_pkg ); echo \"RC=\$?\"" 2>&1 ) +} + +_out="$(_run_apt false true)" +assert_contains "optional: returns 2 so the caller can continue" "$_out" "RC=2" +assert_not_contains "optional: no sudo prompt" "$_out" "elevated permissions" +assert_not_contains "optional: sudo never invoked" "$_out" "ELEVATION_ATTEMPTED" + +_out="$(_run_apt true true)" +assert_contains "optional in Tauri: returns 2" "$_out" "RC=2" +assert_not_contains "optional in Tauri: no NEED_SUDO dialog" "$_out" "NEED_SUDO" + +_out="$(_run_apt false false)" +assert_contains "required: still escalates" "$_out" "ELEVATION_ATTEMPTED" + +_out="$(_run_apt true false)" +assert_contains "required in Tauri: still asks Rust to elevate" "$_out" "NEED_SUDO" + +rm -f "$_APT_FN" +rm -rf "$_BIN" "$_FN_FILE" "$_HARNESS" +echo "" +echo "=== $PASS passed, $FAIL failed ===" +[ "$FAIL" -eq 0 ] diff --git a/tests/sh/test_macos_clt_gate.sh b/tests/sh/test_macos_clt_gate.sh new file mode 100755 index 0000000000..2779df191e --- /dev/null +++ b/tests/sh/test_macos_clt_gate.sh @@ -0,0 +1,165 @@ +#!/bin/bash +# SPDX-License-Identifier: AGPL-3.0-only +# Copyright 2026-present the Unsloth AI Inc. team. All rights reserved. See /studio/LICENSE.AGPL-3.0 +# +# Guards the macOS system-dependency gate in install.sh. +# +# History: the gate was inline top-level code running +# xcode-select -p || { xcode-select --install; exit 1; } +# so a brand-new Mac could not install at all, and being inline rather than a function +# it was out of reach of the tests/sh sed-extraction convention that would have caught +# it. +# +# The contract now: a consumer install must SUCCEED with no Xcode Command Line Tools +# (uv, CPython, llama.cpp/whisper.cpp/Node are all prebuilt, triton is skipped on +# macOS), while `--local` must still fail loudly: unsloth-zoo comes from a git+https +# URL. +set -e + +SCRIPT_DIR="$(cd "$(dirname "$0")" && pwd)" +INSTALL_SH="$SCRIPT_DIR/../../install.sh" +PASS=0 +FAIL=0 + +assert_eq() { + _label="$1"; _expected="$2"; _actual="$3" + if [ "$_actual" = "$_expected" ]; then + echo " PASS: $_label" + PASS=$((PASS + 1)) + else + echo " FAIL: $_label (expected '$_expected', got '$_actual')" + FAIL=$((FAIL + 1)) + fi +} + +assert_contains() { + _label="$1"; _haystack="$2"; _needle="$3" + if echo "$_haystack" | grep -qF "$_needle"; then + echo " PASS: $_label" + PASS=$((PASS + 1)) + else + echo " FAIL: $_label (expected to find '$_needle')" + FAIL=$((FAIL + 1)) + fi +} + +assert_not_contains() { + _label="$1"; _haystack="$2"; _needle="$3" + if echo "$_haystack" | grep -qF "$_needle"; then + echo " FAIL: $_label (found '$_needle' but should not)" + FAIL=$((FAIL + 1)) + else + echo " PASS: $_label" + PASS=$((PASS + 1)) + fi +} + +# ── Extract the functions under test ── +_FN_FILE=$(mktemp) +sed -n '/^_has_working_git()/,/^}/p' "$INSTALL_SH" > "$_FN_FILE" +sed -n '/^_check_macos_deps()/,/^}/p' "$INSTALL_SH" >> "$_FN_FILE" + +if ! grep -q '_check_macos_deps()' "$_FN_FILE"; then + echo "FAIL: could not extract _check_macos_deps from install.sh" + echo " (the gate must stay a top-level function so this test can reach it)" + exit 1 +fi + +# Minimal harness: the output helpers install.sh would otherwise provide. +_HARNESS=$(mktemp) +cat > "$_HARNESS" <<'HARNESS' +C_WARN=''; C_ERR=''; C_OK=''; C_DIM=''; C_RST='' +step() { echo "STEP $1 $2"; } +substep() { echo "SUBSTEP $1"; } +tauri_log() { echo "[TAURI:$1] $2"; } +HARNESS + +_BIN=$(mktemp -d) + +# Each tool is absent, a working stub, or a broken stub mimicking the Xcode CLT shim +# (exists, exits non-zero). +_mk() { printf '#!/bin/sh\n%s\n' "$2" > "$_BIN/$1"; chmod +x "$_BIN/$1"; } + +# PATH is the sandbox and ONLY the sandbox, so unstocked tools are genuinely absent and +# the host's /usr/bin/git cannot leak in. bash must therefore be invoked absolutely. +_SH="${BASH:-/bin/bash}" + +_run_gate() { + # $1 = STUDIO_LOCAL_INSTALL + ( PATH="$_BIN"; export PATH + "$_SH" -c ". '$_HARNESS'; . '$_FN_FILE'; STUDIO_LOCAL_INSTALL=$1; _check_macos_deps; echo \"RC=\$?\"" 2>&1 ) +} + +echo "=== clean Mac: no CLT at all (xcode-select missing) ===" +rm -f "$_BIN"/* +_out="$(_run_gate false)" +assert_contains "does not exit 1" "$_out" "RC=0" +assert_contains "says CLT are not required" "$_out" "not required" +assert_not_contains "never claims CLT are required" "$_out" "are required" + +echo "=== clean Mac: CLT stubs present but non-functional (the real virgin-Mac shape) ===" +# With no CLT, /usr/bin/git EXISTS and fails when run, so `command -v git` succeeds. +# The gate must not be fooled by that. +rm -f "$_BIN"/* +_mk xcode-select 'exit 1' +_mk git 'echo "xcrun: error: invalid active developer path" >&2; exit 1' +_out="$(_run_gate false)" +assert_contains "consumer install proceeds" "$_out" "RC=0" +assert_contains "reports CLT absent but optional" "$_out" "not required" + +echo "=== --local with a non-functional git: must fail loudly ===" +_out="$(_run_gate true)" +assert_contains "fails" "$_out" "RC=1" +assert_contains "explains why git is needed" "$_out" "unsloth-zoo" +assert_contains "names the remedy" "$_out" "xcode-select --install" +assert_contains "emits a machine-readable marker" "$_out" "[TAURI:NEED_XCODE_CLT]" +assert_contains "says a normal install needs none" "$_out" "non---local" + +echo "=== --local with a working git: proceeds ===" +rm -f "$_BIN"/* +_mk xcode-select 'exit 1' +_mk git 'echo "git version 2.50.0"; exit 0' +_out="$(_run_gate true)" +assert_contains "--local proceeds when git works" "$_out" "RC=0" + +echo "=== CLT installed + cmake present ===" +rm -f "$_BIN"/* +_mk xcode-select 'echo /Library/Developer/CommandLineTools; exit 0' +_mk git 'echo "git version 2.50.0"; exit 0' +_mk cmake 'echo "cmake version 3.30.0"; exit 0' +_out="$(_run_gate false)" +assert_contains "all deps found" "$_out" "all system dependencies found" +assert_contains "rc 0" "$_out" "RC=0" + +echo "=== CLT installed, cmake missing: prebuilt path, not fatal ===" +rm -f "$_BIN"/* +_mk xcode-select 'echo /Library/Developer/CommandLineTools; exit 0' +_mk git 'echo "git version 2.50.0"; exit 0' +_out="$(_run_gate false)" +assert_contains "uses prebuilt llama.cpp" "$_out" "using prebuilt llama.cpp" +assert_contains "rc 0" "$_out" "RC=0" + +echo "=== the gate never fires the GUI installer on the consumer path ===" +# The dialog needs a GUI session a curl-piped or Tauri-spawned install does not have. +rm -f "$_BIN"/* +_mk xcode-select 'if [ "$1" = "--install" ]; then echo "GUI-DIALOG-FIRED"; fi; exit 1' +_out="$(_run_gate false)" +assert_not_contains "no GUI dialog on consumer path" "$_out" "GUI-DIALOG-FIRED" + +echo "=== _has_working_git distinguishes present-but-broken from working ===" +rm -f "$_BIN"/* +_mk git 'exit 1' +_r="$(PATH="$_BIN" "$_SH" -c ". '$_FN_FILE'; _has_working_git && echo yes || echo no")" +assert_eq "broken git stub -> no" "no" "$_r" +_mk git 'echo ok; exit 0' +_r="$(PATH="$_BIN" "$_SH" -c ". '$_FN_FILE'; _has_working_git && echo yes || echo no")" +assert_eq "working git -> yes" "yes" "$_r" +rm -f "$_BIN"/git +_r="$(PATH="$_BIN" "$_SH" -c ". '$_FN_FILE'; _has_working_git && echo yes || echo no")" +assert_eq "absent git -> no" "no" "$_r" + +rm -rf "$_BIN" "$_FN_FILE" "$_HARNESS" + +echo "" +echo "=== $PASS passed, $FAIL failed ===" +[ "$FAIL" -eq 0 ] || exit 1 diff --git a/tests/studio/install/test_rocm_support.py b/tests/studio/install/test_rocm_support.py index b003382859..51c2d6587c 100644 --- a/tests/studio/install/test_rocm_support.py +++ b/tests/studio/install/test_rocm_support.py @@ -3157,12 +3157,35 @@ class TestInstallBnbWindowsRocm: assert result is False assert "BNB_ROCM_VERSION" not in os.environ - def test_no_op_when_win_amd64_url_missing(self): - """Should be silent no-op if win_amd64 key absent from _BNB_ROCM_PRERELEASE_URLS.""" + def test_falls_back_to_pypi_when_win_amd64_url_missing(self): + """No win_amd64 pre-release wheel must not mean no bitsandbytes: PyPI + >=0.50.0 ships libbitsandbytes_rocm{714,72}.dll, so it is a real ROCm build.""" with patch.object(stack_mod, "_BNB_ROCM_PRERELEASE_URLS", {}): - with patch.object(stack_mod, "pip_install_try") as mock_pip: + with patch.object(stack_mod, "pip_install_try", return_value = True) as mock_pip: stack_mod._install_bnb_windows_rocm() - mock_pip.assert_not_called() + assert mock_pip.call_count == 1 + assert stack_mod._BNB_ROCM_PYPI_FALLBACK in mock_pip.call_args.args + + def test_falls_back_to_pypi_when_prerelease_install_fails(self): + """A blocked GitHub pre-release URL must fall through to the PyPI floor rather + than leaving Windows ROCm with no working bitsandbytes.""" + with patch.object(stack_mod, "pip_install_try", side_effect = [False, True]) as mock_pip: + with patch.object(stack_mod, "_detect_bnb_rocm_dll_ver", return_value = "72"): + result = stack_mod._install_bnb_windows_rocm() + assert result is True + assert mock_pip.call_count == 2 + assert "win_amd64" in str(mock_pip.call_args_list[0]) + assert stack_mod._BNB_ROCM_PYPI_FALLBACK in mock_pip.call_args_list[1].args + + def test_returns_false_only_when_both_paths_fail(self): + """Both the pre-release wheel and the PyPI fallback must fail before the + helper reports failure.""" + with patch.dict(os.environ, {}, clear = False): + os.environ.pop("BNB_ROCM_VERSION", None) + with patch.object(stack_mod, "pip_install_try", return_value = False) as mock_pip: + result = stack_mod._install_bnb_windows_rocm() + assert result is False + assert mock_pip.call_count == 2 def test_sets_bnb_rocm_version_from_detected_dll(self): """BNB_ROCM_VERSION is set from the DLL detected after install.""" diff --git a/tests/studio/test_chat_preset_load_config.py b/tests/studio/test_chat_preset_load_config.py index 1588c7d96d..6234ab395c 100644 --- a/tests/studio/test_chat_preset_load_config.py +++ b/tests/studio/test_chat_preset_load_config.py @@ -68,3 +68,18 @@ def test_backend_chat_preset_accepts_load_config(): routes = _read("studio/backend/routes/chat_history.py") assert "class ChatPresetLoadConfig" in routes assert "loadConfig: Optional[ChatPresetLoadConfig]" in routes + + +def test_preset_load_config_carries_parallel_slots(): + # Captured, clamped on read, applied, and accepted by the extra="forbid" + # backend model (a missing backend field would 422 every settings sync). + source = _read("studio/frontend/src/features/chat/presets/preset-load-config.ts") + assert '| "nParallel"' in source + assert "nParallel: snapshot.nParallel ?? null" in source + assert "nParallel: config.nParallel ?? null" in source + assert "N_PARALLEL_MAX, Math.round(partial.nParallel)" in source + routes = _read("studio/backend/routes/chat_history.py") + assert ( + "nParallel: Optional[int] = Field(default = None, ge = PARALLEL_MIN, le = PARALLEL_MAX)" + in routes + ) diff --git a/tests/studio/test_model_picker_contracts.py b/tests/studio/test_model_picker_contracts.py index 00ee83efc7..d9a8efc9a4 100644 --- a/tests/studio/test_model_picker_contracts.py +++ b/tests/studio/test_model_picker_contracts.py @@ -631,6 +631,253 @@ def test_legacy_migration_is_idempotent_and_non_destructive(): assert "if (isDefaultConfig(migrated) || Object.hasOwn(map, key)) {" in src +def test_parallel_slots_setting_wired_end_to_end(): + """The per-load Parallel Slots knob (llama-server --parallel) must flow from + the run-settings form through persistence, every /load builder, the validate + preflight and the cross-model reset; a lost hop silently reverts the model to + the server-wide slot default.""" + config = _read("features/model-picker/model-config/per-model-config.ts") + # Persisted per model, clamped on every read/write, and null (= server + # default) counts as default so blank configs are not stored. + assert '"nParallel",' in config + assert "N_PARALLEL_MAX, Math.round(partial.nParallel)" in config + assert "config.nParallel == null &&" in config + page = _read("features/model-picker/components/model-config-page.tsx") + # Rendered in the GGUF advanced section, which a remembered override reopens. + assert "Parallel Slots" in page + assert "config.nParallel != null ||" in page + assert 'aria-label="Parallel decode slots"' in page + api_types = _read("features/chat/types/api.ts") + assert "n_parallel?: number | null;" in api_types + runtime = _read("features/chat/hooks/use-chat-model-runtime.ts") + # Click-time snapshot, /load body, validate preflight, cross-model reset and + # failed-switch rollback all carry the value. + assert "pendingLoadConfig?.nParallel" in runtime + # GGUF-gated, like the compare pane: a transformers load has no slots. + assert "n_parallel: isGguf ? loadNParallel : null," in runtime + assert "n_parallel: validateNParallel," in runtime + assert "loadNParallel = pendingLoadConfig?.nParallel ?? null;" in runtime + assert "n_parallel: stateBeforeUnload.loadedNParallel," in runtime + chat_api = _read("features/chat/api/chat-api.ts") + assert "n_parallel: payload.n_parallel," in chat_api + composer = _read("features/chat/shared-composer.tsx") + # The compare pane is a second /load builder; its preflight sizes like its load. + assert composer.count("n_parallel: ownConfig.nParallel ?? null,") == 2 + adapter = _read("features/chat/api/chat-adapter.ts") + # The startup auto-load is a third builder reading the remembered config. + assert adapter.count("n_parallel: config.nParallel ?? null,") == 2 + # ... and records it as loaded through the diffusion-gated local below. + assert "loadedNParallel: committedSlots," in adapter + status = _read("features/chat/lib/apply-inference-status-to-store.ts") + # Hydration seeds the rollback BASELINE only; adopting the resolved echo into + # the control would pin a blank "server default" to a number. + assert "loadedNParallel: status.requested_parallel_slots," in status + assert "nParallel: status.requested_parallel_slots," not in status + sidebar = _read("features/model-picker/components/sidebar-model-config.tsx") + # The sidebar form remounts when an external change lands. + assert 'config.nParallel ?? "",' in sidebar + + +def test_parallel_slots_control_cleared_when_the_load_never_sent_them(): + """`nParallel` is the editable control ("blank = follow the server default") + and `loadedNParallel` the rollback baseline. A success path that sends no + slot count must blank the control, or a value staged for another model shows + as applied, is persisted into this model's config (`isDefaultConfig` keys on + nParallel) and is re-sent by the next Apply. Each assertion below is the only + thing pinning one such path.""" + status = " ".join(_read("features/chat/lib/apply-inference-status-to-store.ts").split()) + # A model/variant swap underneath this tab must reset the control like + # performLoad's cross-model reset, or model A's count follows onto model B. + # Narrowly gated -- see test_hydration_keeps_the_slot_control_when_readopting_the_running_model. + assert "...(seedLoadParams && slotsModelChanged && { nParallel: null })," in status + # ... while still never adopting the RESOLVED echo into the control. + assert "nParallel: status.requested_parallel_slots," not in status + + adapter = _read("features/chat/api/chat-adapter.ts") + # Slice the two success branches apart, bounding the second at the shared tail + # so it cannot swallow the fresh-default path below and stay green. + candidate = adapter.split("async function loadAutoLoadCandidate", 1)[1] + gguf_branch, non_gguf_rest = candidate.split('if (candidate.kind === "gguf") {', 1)[1].split( + "\n } else {\n", 1 + ) + non_gguf_branch = non_gguf_rest.split("if (!(loadResp.is_lora ?? false)) {", 1)[0] + # The cached-GGUF branch keeps the remembered override via the gated local... + assert "nParallel: committedSlots," in gguf_branch + assert "nParallel: null," not in gguf_branch + # ... the safetensors fallback sends no slots, so it clears both, or the count + # survives on a model whose form does not even render the field. + assert "nParallel: null," in non_gguf_branch + assert "loadedNParallel: null," in non_gguf_branch + + fresh_default = adapter.split("No downloaded models found. Fetching", 1)[1].split( + 'showAutoLoadSuccess("Loaded Qwen', 1 + )[0] + # The fresh-default download omits the slots, so its success state clears both, + # or the control reads as an unapplied edit against the seeded baseline. + assert "n_parallel" not in fresh_default.split("saveSpeculativeType", 1)[0] + assert "nParallel: null," in fresh_default + assert "loadedNParallel: null," in fresh_default + + +def test_hydration_clears_the_slot_baseline_for_a_slotless_model(): + """The baseline is what a rollback re-sends and what preset capture reads, so + a model that cannot have slots must not inherit the previous GGUF's count. + /status omits the echo for non-GGUF and sends an explicit null for diffusion; + an absent field on a GGUF is an older backend and must NOT wipe it.""" + src = _read("features/chat/lib/apply-inference-status-to-store.ts") + assert ( + "(status.is_gguf === false || status.requested_parallel_slots === null) && {" in src + ), "the slotless clear must key on is_gguf or an explicit null echo" + clear = src.index("status.is_gguf === false || status.requested_parallel_slots === null") + assert "loadedNParallel: null," in src[clear : clear + 200] + # Never `!= null`: that also matches the absent field an older backend sends. + assert "status.requested_parallel_slots !== null && {" not in src + + +def test_hydration_keeps_the_slot_control_when_readopting_the_running_model(): + """`hydratingExistingModel` is true whenever the incoming status disagrees + with what this tab last recorded, which includes RE-ADOPTING a model the tab + never lost: the resident-adopt branch restores the model's own per-model + config and only then hydrates, passing the EXTERNAL id as + `previousCheckpoint`. An ungated clear there wipes the slot count that branch + just restored, and the blank persists into `savePerModelConfig`, so a Save + the user reads as a no-op erases their remembered override. + + Only that branch knows the model is unchanged, so it says so explicitly. + Slot counts cannot stand in: the echo falls back to the server-wide default, + so a genuine A->B swap can echo exactly A's explicit count.""" + status = " ".join(_read("features/chat/lib/apply-inference-status-to-store.ts").split()) + assert ( + "const slotsModelChanged = hydratingExistingModel && !options.readoptingSameModel;" + in status + ) + assert "...(seedLoadParams && slotsModelChanged && { nParallel: null })," in status + # Never a slot-count proxy for "same model". + assert "prevState.loadedNParallel === (status.requested_parallel_slots" not in status + # The baseline seed stays ungated, or a rollback after a tab reload restores + # the model at the server default slots. + assert "loadedNParallel: status.requested_parallel_slots," in status + + runtime = " ".join(_read("features/chat/hooks/use-chat-model-runtime.ts").split()) + resident = runtime.split("if (!forceReload && isExternalModelId(selectedCheckpoint)) {", 1)[ + 1 + ].split("const stopDecision", 1)[0] + # What makes the scenario reachable: the branch restores the model's own + # config, then hydrates against the external id. + assert "applyPerModelConfigToRuntime(selection.previousConfig);" in resident + assert "previousCheckpoint: selectedCheckpoint," in resident + # Only reachable because the branch matched the id AND the variant first. + assert "resolveInferenceCheckpointId(residentStatus) === modelId" in resident + assert "readoptingSameModel: true," in resident + # The refresh() hydrate must NOT claim it: there the model really can change. + poll = runtime.split("setModels(listRes.models.map(toChatModelSummary));", 1)[1].split( + "} else if (!statusRes.active_model", 1 + )[0] + assert "applyActiveModelStatusToStore(statusRes, {" in poll + assert "readoptingSameModel" not in poll + + +def test_parallel_slots_are_never_recorded_for_a_diffusion_load(): + """A DiffusionGemma GGUF answers ``is_gguf: true``, but its runner ignores + ``--parallel``, so ``_parallel_slot_echo`` reports null slots for it. The + three load success paths must gate on ``is_diffusion`` too, or they record a + click-time count the load never committed. + + That phantom does not stay put: ``capturePresetLoadConfig`` snapshots + ``nParallel`` with no model gate and a preset carries no model identity, so + applying it over a TEXT GGUF sends the count as a real ``n_parallel``. + """ + runtime = " ".join(_read("features/chat/hooks/use-chat-model-runtime.ts").split()) + # One gated local feeds the control and the baseline, so they cannot drift. + assert "(loadResponse.is_gguf ?? false) && !(loadResponse.is_diffusion ?? false)" in runtime + assert "nParallel: committedSlots," in runtime + assert "loadedNParallel: committedSlots," in runtime + + adapter = " ".join(_read("features/chat/api/chat-adapter.ts").split()) + assert ( + "const committedSlots = (loadResp.is_diffusion ?? false) ? null " + ": (config.nParallel ?? null);" in adapter + ) + assert "nParallel: committedSlots," in adapter + assert "loadedNParallel: committedSlots," in adapter + + composer = " ".join(_read("features/chat/shared-composer.tsx").split()) + assert "targetIsGguf && !(resp.is_diffusion ?? false)" in composer + assert "nParallel: committedSlots," in composer + assert "loadedNParallel: committedSlots," in composer + + +def test_hydration_restores_a_remembered_slot_override(): + """The control is never seeded from the status echo, so a model running on a + remembered override shows a BLANK slot control after a browser reload or a + tab move to another GGUF. `ModelConfigPage.resolveInitial` prefers the live + store for the active model, so that blank is what the form edits: the next + Apply reloads at the server default and a Save writes the blank over the + remembered count. + + The seed is deliberately narrow: storage is read only on a fresh store or a + model change, never on a steady poll, and the value is adopted only when the + server already runs that exact count, which proves it is this model's own. + """ + src = _read("features/chat/lib/apply-inference-status-to-store.ts") + status = " ".join(src.split()) + assert ( + "resolveInitialConfig(checkpointId, status.gguf_variant ?? null)" in status + ), "the remembered override comes from per-model storage, not the echo" + assert ( + "const slotsUnseeded = prevState.loadedNParallel === null && " + "prevState.nParallel === null;" in status + ) + assert ( + "status.is_gguf && (slotsUnseeded || slotsModelChanged)" in status + ), "storage is read on a fresh store or a model change, never on a steady poll" + assert ( + "...(seedLoadParams && (slotsUnseeded || slotsModelChanged) &&" in status + ), "the seed fires in both cases the clear leaves the control blank" + assert ( + "rememberedNParallel != null && rememberedNParallel === " + "status.requested_parallel_slots && { nParallel: rememberedNParallel, }" in status + ) + # Both cases trip the model-change clear, so the seed only survives by + # being spread after it. + assert src.index("slotsModelChanged && { nParallel: null }") < src.index( + "nParallel: rememberedNParallel," + ) + + +def test_failed_switch_rollback_restores_the_slot_intent_not_the_resolved_count(): + """`loadedNParallel` holds a RESOLVED count even for a load that sent no + slots (the echo falls back to the server-wide default), so it is the right + value to re-send when recreating the previous server and the wrong one to put + back in the control: it turns "follow the server default" into an explicit + override that a later Save or preset capture pins. The outer catch only + repairs that for a staged config, so a plain string pick keeps the phantom. + + The intent comes from the picker's own pre-switch snapshot when there is one: + chat-page pre-applies the TARGET's config before calling selectModel, so the + live control describes the outgoing model only for a bare pick.""" + runtime = " ".join(_read("features/chat/hooks/use-chat-model-runtime.ts").split()) + assert ( + 'const previousNParallel = typeof selection !== "string" && ' + "selection.previousConfig ? (selection.previousConfig.nParallel ?? null) " + ": useChatRuntimeStore.getState().nParallel;" in runtime + ) + assert runtime.index("const previousNParallel") < runtime.index( + "applyPerModelConfigToRuntime(pendingLoadConfig);" + ), "a config staged on the selection must not replace it either" + picker = " ".join(_read("features/chat/chat-page.tsx").split()) + assert ( + "const previousConfig = currentRuntimePerModelConfig({ includeMaxSeqLength: true, }); " + "const hasAppliedConfig = applyModelLoadConfigToRuntime(" in picker + ), "the snapshot must be taken before the target's config is applied" + rollback = runtime.split("const rollbackSpeculativeType", 1)[1] + assert "nParallel: previousNParallel," in rollback + # Baseline and reload payload keep the resolved count, or the rollback + # recreates the previous model at a different slot count. + assert "loadedNParallel: stateBeforeUnload.loadedNParallel ?? null," in rollback + assert "n_parallel: stateBeforeUnload.loadedNParallel," in runtime + + def test_vulkan_inference_devices_are_the_pickable_set(): """GGUF loads run through llama-server, so on a Vulkan build the picker must offer the inference inventory (ggml ordinals, the space `--device Vulkan` diff --git a/tests/test_fp8_tiny_e8m0.py b/tests/test_fp8_tiny_e8m0.py index cf49c8c92f..df40879d5a 100644 --- a/tests/test_fp8_tiny_e8m0.py +++ b/tests/test_fp8_tiny_e8m0.py @@ -11,7 +11,11 @@ dequant reference. import pytest import torch -pytestmark = pytest.mark.skipif(not torch.cuda.is_available(), reason = "needs CUDA") +cuda_available = torch.cuda.is_available() +xpu_available = hasattr(torch, "xpu") and torch.xpu.is_available() +dev = "cuda" if cuda_available else "xpu" if xpu_available else "cpu" + +pytestmark = pytest.mark.skipif(not (cuda_available or xpu_available), reason = "needs CUDA or XPU") def _reference(X, weight, scale, block): @@ -27,7 +31,6 @@ def test_tiny_non_tileable_forward_backward_matches_reference(): from unsloth.kernels.fp8 import FP8BlockQuantLinear torch.manual_seed(0) - dev = "cuda" block = [128, 128] m, n = 8, 8 # non-tileable, in-dim % 128 != 0 weight = torch.randn(m, n, device = dev, dtype = torch.bfloat16) # (out=m, in=n) @@ -50,7 +53,6 @@ def test_e8m0_scale_is_upcast_and_runs(): if not hasattr(torch, "float8_e8m0fnu"): pytest.skip("torch build lacks float8_e8m0fnu") - dev = "cuda" m, n = 8, 8 weight = torch.randn(m, n, device = dev, dtype = torch.bfloat16) scale = (torch.rand(1, 1, device = dev) + 1.0).to(torch.float8_e8m0fnu) @@ -70,7 +72,6 @@ def test_rectangular_block_dequant_matches_reference(): from unsloth.kernels.fp8 import _blockwise_weight_dequant_any_shape torch.manual_seed(0) - dev = "cuda" block = [64, 128] m, n = 64, 256 # evenly tiled: 64 % 64 == 0, 256 % 128 == 0 weight = torch.randn(m, n, device = dev, dtype = torch.bfloat16) @@ -94,7 +95,6 @@ def test_e8m0_scale_preserves_non_default_block_size_attr(): pytest.skip("torch build lacks float8_e8m0fnu") torch.manual_seed(0) - dev = "cuda" block = [64, 64] # in-dim 96 is not divisible by block[1]=64 -> forward takes the torch dequant # fallback (no fp8 matmul kernel). Scale shape (2, 2) validates for [64, 64] but diff --git a/tests/test_new_mapper_fetched_fp8.py b/tests/test_new_mapper_fetched_fp8.py index 2835aadb59..bdd1b241fa 100644 --- a/tests/test_new_mapper_fetched_fp8.py +++ b/tests/test_new_mapper_fetched_fp8.py @@ -14,6 +14,11 @@ Two gaps it misses: future rename): reading them with ``[]`` raises ``KeyError`` into the bare ``except``, taking the 4bit half, the probe's whole purpose, down with it. +Both of the above only reach the block table. The last two tests take the row branch, which +``load_in_fp8 = True`` plus ``UNSLOTH_HAS_FBGEMM`` selects ahead of block: deleting that branch, +or dropping ``_resolve_with_mappers``' ``fp8_row`` argument so it falls back to the installed +table, both leave every other test here green. + ``loader_utils`` imports torch, so ast-extract the resolvers and run them against a stubbed ``requests``, as in ``tests/test_bad_mappings_redirect.py``. """ @@ -33,6 +38,8 @@ _NEW_OFFICIAL = "zeta-org/Zeta-9B-Only-On-Main-FP8" _NEW_BLOCK = "unsloth/Zeta-9B-Only-On-Main-FP8-Block" _NEW_ROW = "unsloth/Zeta-9B-Only-On-Main-FP8-Row" _ANCHOR = ' "unsloth/Kimi-K2-Instruct-BF16" : (' +# Row table only, so the block branch cannot answer for it and mask a row-path regression. +_ROW_ONLY = "zeta-org/Zeta-9B-Row-Only-FP8" def _mapper_source(): @@ -51,6 +58,11 @@ def _with_extra_fp8_model(source): return source.replace(_ANCHOR, entry + _ANCHOR, 1) +def _with_row_only_fp8_model(source): + """Fetched row table only. Block must not know it, or the block branch answers instead.""" + return source + f'\nFLOAT_TO_FP8_ROW_MAPPER["{_ROW_ONLY.lower()}"] = "{_NEW_ROW}"\n' + + def _without_fp8_tables(source): """A mapper.py from before the fp8 tables existed.""" return source.replace("FLOAT_TO_FP8_BLOCK_MAPPER", "SOME_OTHER_BLOCK_TABLE").replace( @@ -153,3 +165,44 @@ def test_probe_survives_a_fetched_mapper_without_the_fp8_tables(monkeypatch): assert ( int_to_float and float_to_int and map_to_16bit ), "a fetched mapper.py without the fp8 tables must not take the 4bit upgrade check down" + + +def test_fbgemm_prefers_the_row_table_over_the_block_one(monkeypatch): + """With FBGEMM, `load_in_fp8 = True` must resolve row-scaled, not blockwise.""" + monkeypatch.setenv("UNSLOTH_HAS_FBGEMM", "1") + namespace = _load_resolver(_mapper_source()) + row = namespace["FLOAT_TO_FP8_ROW_MAPPER"] + block = namespace["FLOAT_TO_FP8_BLOCK_MAPPER"] + + key = next(k for k in row if k in block and row[k] != block[k]) + resolved = namespace["get_model_name"](key, load_in_4bit = False, load_in_fp8 = True) + + assert resolved == row[key], ( + f"FBGEMM must take the row branch for {key!r}, got {resolved!r} " + f"(the blockwise answer is {block[key]!r})" + ) + + +def test_probe_answers_for_a_row_only_repo_the_fetched_mapper_knows(monkeypatch): + """The row half of the probe needs the FETCHED row table, same as the block half.""" + monkeypatch.setenv("UNSLOTH_HAS_FBGEMM", "1") + installed = _mapper_source() + namespace = _load_resolver(installed) + installed_row = namespace["FLOAT_TO_FP8_ROW_MAPPER"] + key = _ROW_ONLY.lower() + assert key not in installed_row, "the installed row table must not know it" + assert key not in namespace["FLOAT_TO_FP8_BLOCK_MAPPER"], "no block entry, or block answers" + + _install_fake_requests(monkeypatch, _with_row_only_fp8_model(installed)) + _install_fake_vllm_absent(monkeypatch, namespace) + + try: + resolved = namespace["get_model_name"](_ROW_ONLY, load_in_4bit = False, load_in_fp8 = True) + except NotImplementedError as error: + assert "not supported in your current Unsloth version" in str(error) + else: + raise AssertionError( + f"a fetched-only row-scaled repo must raise the upgrade error, got {resolved!r}" + ) + + assert namespace["FLOAT_TO_FP8_ROW_MAPPER"] is installed_row diff --git a/tests/test_raw_text_json_loading.py b/tests/test_raw_text_json_loading.py new file mode 100644 index 0000000000..27e636da18 --- /dev/null +++ b/tests/test_raw_text_json_loading.py @@ -0,0 +1,128 @@ +"""Regression test for .json parsing in unsloth/dataprep/raw_text.py. + +Both .json and .jsonl map to the "json_lines" handler, which used to parse the +file one line at a time. A real .json file is a single JSON document (commonly +a top-level list of records), so every line failed json.loads, the whole +document was dropped, and the handler returned "" (load_from_file then rejected +the valid file as "empty"). The handler now parses the file as one JSON value +first and falls back to line-by-line for true .jsonl. + +raw_text.py's only third-party import is `datasets`, so we stub it and exec the +module directly, with no `import unsloth` (which needs a GPU / unsloth_zoo). +""" + +import json +import sys +import types +from pathlib import Path + +RAW_TEXT_PATH = Path(__file__).parents[1] / "unsloth" / "dataprep" / "raw_text.py" + + +def _load_raw_text(): + sys.modules.setdefault("datasets", types.SimpleNamespace(Dataset = object)) + module = types.ModuleType("unsloth_raw_text_under_test") + exec( + compile(RAW_TEXT_PATH.read_text(encoding = "utf-8"), str(RAW_TEXT_PATH), "exec"), + module.__dict__, + ) + return module + + +def test_json_document_is_parsed_whole(tmp_path): + loader = _load_raw_text().RawTextDataLoader(tokenizer = object()) + path = tmp_path / "data.json" + path.write_text( + json.dumps([{"text": "hello world"}, {"text": "second sample"}], indent = 2), encoding = "utf-8" + ) + assert loader._read_file_by_format(str(path), "json_lines") == "hello world\n\nsecond sample" + + +def test_jsonl_is_still_parsed_line_by_line(tmp_path): + loader = _load_raw_text().RawTextDataLoader(tokenizer = object()) + path = tmp_path / "data.jsonl" + path.write_text('{"text": "a"}\n{"text": "b"}\n', encoding = "utf-8") + assert loader._read_file_by_format(str(path), "json_lines") == "a\n\nb" + + +def test_jsonl_is_never_materialized(tmp_path): + """A .jsonl file must keep streaming, whole-document parsing is only for .json.""" + real_open = open + + class _StreamOnlyFile: + """File wrapper that fails the test if the whole file is pulled into memory.""" + + def __init__(self, handle): + self.handle = handle + + def __enter__(self): + return self + + def __exit__(self, *exc_info): + self.handle.close() + return False + + def __iter__(self): + return iter(self.handle) + + def read(self, *args, **kwargs): + raise AssertionError(".jsonl was read whole instead of streamed line by line") + + def seek(self, *args, **kwargs): + raise AssertionError(".jsonl was re-read instead of streamed line by line") + + module = _load_raw_text() + module.open = lambda *args, **kwargs: _StreamOnlyFile(real_open(*args, **kwargs)) + + path = tmp_path / "big.jsonl" + path.write_text('{"text": "a"}\n\n{"text": "b"}\nnot json at all\n', encoding = "utf-8") + loader = module.RawTextDataLoader(tokenizer = object()) + assert loader._read_file_by_format(str(path), "json_lines") == "a\n\nb" + + +def test_json_holding_json_lines_still_falls_back(tmp_path): + """A .json file that actually holds JSON Lines still parses, via the per-line fallback.""" + loader = _load_raw_text().RawTextDataLoader(tokenizer = object()) + path = tmp_path / "mislabelled.json" + path.write_text('{"text": "a"}\n{"text": "b"}\n', encoding = "utf-8") + assert loader._read_file_by_format(str(path), "json_lines") == "a\n\nb" + + +def test_utf8_bom_json_document_is_parsed(tmp_path): + """Windows tooling prefixes a UTF-8 BOM; it must not sink the whole document.""" + loader = _load_raw_text().RawTextDataLoader(tokenizer = object()) + path = tmp_path / "bom.json" + path.write_text( + json.dumps([{"text": "hello world"}, {"text": "second sample"}], indent = 2), + encoding = "utf-8-sig", + ) + assert path.read_bytes().startswith(b"\xef\xbb\xbf") + assert loader._read_file_by_format(str(path), "json_lines") == "hello world\n\nsecond sample" + + +def test_utf8_bom_jsonl_keeps_first_record(tmp_path): + """A BOM must not silently drop the first .jsonl record.""" + loader = _load_raw_text().RawTextDataLoader(tokenizer = object()) + path = tmp_path / "bom.jsonl" + path.write_text('{"text": "a"}\n{"text": "b"}\n', encoding = "utf-8-sig") + assert loader._read_file_by_format(str(path), "json_lines") == "a\n\nb" + + +def test_utf8_bom_json_holding_json_lines_falls_back(tmp_path): + """The per-line fallback re-reads from byte 0, so the BOM must be stripped again.""" + loader = _load_raw_text().RawTextDataLoader(tokenizer = object()) + path = tmp_path / "bom_mislabelled.json" + path.write_text('{"text": "a"}\n{"text": "b"}\n', encoding = "utf-8-sig") + assert loader._read_file_by_format(str(path), "json_lines") == "a\n\nb" + + +def test_utf8_bom_plain_text_and_csv(tmp_path): + """The BOM also leaks into .txt training text and the first .csv column name.""" + loader = _load_raw_text().RawTextDataLoader(tokenizer = object()) + txt = tmp_path / "bom.txt" + txt.write_text("hello", encoding = "utf-8-sig") + assert loader._read_file_by_format(str(txt), "plain_text") == "hello" + + csv_path = tmp_path / "bom.csv" + csv_path.write_text("text,other\nhello,x\n", encoding = "utf-8-sig") + assert loader._read_file_by_format(str(csv_path), "csv_text_column") == "hello" diff --git a/tests/utils/perplexity_eval.py b/tests/utils/perplexity_eval.py index 5f33a24d53..cdd30e5511 100644 --- a/tests/utils/perplexity_eval.py +++ b/tests/utils/perplexity_eval.py @@ -2,6 +2,9 @@ from tqdm import tqdm import torch import pandas as pd +# DEVICE_TYPE_TORCH, not DEVICE_TYPE: the latter can be "hip"/"mlx", which .to() rejects. +from unsloth.device_type import DEVICE_TYPE_TORCH + model_comparison_results = {} @@ -17,7 +20,7 @@ def ppl_model(model, tokenizer, dataset): for begin_loc in range(0, seq_len, stride): end_loc = min(begin_loc + max_length, seq_len) trg_len = end_loc - prev_end_loc - input_ids = encodings.input_ids[:, begin_loc:end_loc].to("cuda") + input_ids = encodings.input_ids[:, begin_loc:end_loc].to(DEVICE_TYPE_TORCH) target_ids = input_ids.clone() target_ids[:, :-trg_len] = -100 pad_token_id = tokenizer.pad_token_id if tokenizer.pad_token_id is not None else 0 diff --git a/tests/utils/test_batched_leftpad_generation_gpu.py b/tests/utils/test_batched_leftpad_generation_gpu.py index df03125bc2..13db22461e 100644 --- a/tests/utils/test_batched_leftpad_generation_gpu.py +++ b/tests/utils/test_batched_leftpad_generation_gpu.py @@ -4,7 +4,7 @@ Greedy generation in a left-padded batch must match solo batch-size-1 generation for the first PREFIX_TOKENS tokens (the bug makes padded rows diverge into garbage immediately; a full-length match would be flaky due to benign batch-numerics tie-flips deep in the sequence) and must not be -gibberish. Skipped without CUDA. Run: `python -m pytest +gibberish. Skipped without a GPU. Run: `python -m pytest tests/utils/test_batched_leftpad_generation_gpu.py -v`. """ @@ -12,8 +12,19 @@ import pytest import torch cuda_available = torch.cuda.is_available() +xpu_available = hasattr(torch, "xpu") and torch.xpu.is_available() +device = "cuda" if cuda_available else "xpu" if xpu_available else "cpu" -pytestmark = pytest.mark.skipif(not cuda_available, reason = "requires a CUDA GPU") +# Non-strict rather than CUDA-only: keeps the XPU divergence visible, and goes +# green by itself once XPU generation is fixed. +pytestmark = [ + pytest.mark.skipif(not (cuda_available or xpu_available), reason = "requires a CUDA or XPU GPU"), + pytest.mark.xfail( + xpu_available and not cuda_available, + reason = "batched left-padded generation diverges on XPU", + strict = False, + ), +] MODEL_NAME = "unsloth/Qwen2.5-0.5B-Instruct" MAX_NEW_TOKENS = 32 @@ -53,7 +64,7 @@ def _chat(tokenizer, prompt): def _generate(model, tokenizer, texts): inputs = tokenizer(texts, return_tensors = "pt", padding = True, add_special_tokens = False).to( - "cuda" + device ) with torch.inference_mode(): out = model.generate( diff --git a/tests/utils/test_packing.py b/tests/utils/test_packing.py index 1b8bb65058..0be3018cde 100644 --- a/tests/utils/test_packing.py +++ b/tests/utils/test_packing.py @@ -44,6 +44,8 @@ def _build_packed_training_setup(tmp_path, device): dtype = torch.bfloat16 else: dtype = torch.float16 + elif device.type == "xpu": + dtype = torch.bfloat16 try: model, tokenizer = FastLanguageModel.from_pretrained( @@ -76,8 +78,8 @@ def _build_packed_training_setup(tmp_path, device): max_length = 64, logging_steps = 1, max_steps = 1, - fp16 = device.type == "cuda" and not torch.cuda.is_bf16_supported(), - bf16 = device.type == "cuda" and torch.cuda.is_bf16_supported(), + fp16 = dtype == torch.float16, + bf16 = dtype == torch.bfloat16, dataset_num_proc = 1, output_dir = str(tmp_path), packing = True, @@ -974,7 +976,12 @@ def test_enable_sample_packing(): def test_enable_sample_packing_trl_collator(tmp_path): - device = torch.device("cuda") if torch.cuda.is_available() else torch.device("cpu") + if torch.cuda.is_available(): + device = torch.device("cuda") + elif torch.xpu.is_available(): + device = torch.device("xpu") + else: + device = torch.device("cpu") model, _, trainer, _ = _build_packed_training_setup(tmp_path, device) enable_sample_packing(model, trainer) @@ -1030,7 +1037,12 @@ def test_enable_padding_free_metadata(): def test_packing_sdpa(tmp_path): - device = torch.device("cuda") if torch.cuda.is_available() else torch.device("cpu") + if torch.cuda.is_available(): + device = torch.device("cuda") + elif torch.xpu.is_available(): + device = torch.device("xpu") + else: + device = torch.device("cpu") model, batch, trainer, llama_mod = _build_packed_training_setup(tmp_path, device) assert "packed_seq_lengths" in batch diff --git a/tests/utils/test_qat.py b/tests/utils/test_qat.py index 79d955164f..0b942d5c32 100644 --- a/tests/utils/test_qat.py +++ b/tests/utils/test_qat.py @@ -130,8 +130,14 @@ def _test_fake_quantizers_are_called( # Weight fake quantizers must always be called. assert child.weight_fake_quantizer.count == 1 + if torch.cuda.is_available(): + device = torch.device("cuda") + elif torch.xpu.is_available(): + device = torch.device("xpu") + else: + pytest.skip("No GPU available") for k, v in example_inputs.items(): - example_inputs[k] = v.cuda() + example_inputs[k] = v.to(device) model.apply(_swap_fake_quantizers) model(**example_inputs) model.apply(_assert_fake_quantizers_are_called) diff --git a/tests/utils/test_rope_scaling_drift.py b/tests/utils/test_rope_scaling_drift.py index eba89734f7..7fe4e74d5c 100644 --- a/tests/utils/test_rope_scaling_drift.py +++ b/tests/utils/test_rope_scaling_drift.py @@ -15,18 +15,20 @@ import pytest import torch -def _has_real_cuda(): - try: - torch.zeros(1).to("cuda") - return True - except Exception: - return False +def _has_real_gpu(): + for backend in ("cuda", "xpu"): + try: + torch.zeros(1).to(backend) + return True + except Exception: + pass + return False -HAS_REAL_CUDA = _has_real_cuda() -requires_cuda = pytest.mark.skipif( - not HAS_REAL_CUDA, - reason = "LlamaRotaryEmbedding builds per-device CUDA caches in __init__", +HAS_REAL_GPU = _has_real_gpu() +requires_gpu = pytest.mark.skipif( + not HAS_REAL_GPU, + reason = "LlamaRotaryEmbedding builds per-device caches in __init__ (needs CUDA or XPU)", ) REPO_ROOT = Path(__file__).resolve().parents[2] @@ -360,7 +362,7 @@ def _cos_at_position(rot, position): # --- Layer 3: CUDA behavioral guard (real instantiation needs a device) --- -@requires_cuda +@requires_gpu def test_constructor_applies_llama3_scaling(): config = _make_config(LLAMA3_ROPE_SCALING) rot = _unsloth_rotary(config) @@ -371,7 +373,7 @@ def test_constructor_applies_llama3_scaling(): ), "LlamaRotaryEmbedding built from a llama3 config produced unscaled inv_freq (issue #2405)." -@requires_cuda +@requires_gpu def test_constructor_unscaled_config_uses_vanilla_inv_freq(): rot = _unsloth_rotary(_make_config(None)) got = rot.inv_freq.float().cpu() @@ -381,7 +383,7 @@ def test_constructor_unscaled_config_uses_vanilla_inv_freq(): ), "LlamaRotaryEmbedding with no rope_scaling must use the vanilla inv_freq" -@requires_cuda +@requires_gpu def test_cos_cache_differs_between_scaled_and_unscaled_at_long_position(): scaled = _unsloth_rotary(_make_config(LLAMA3_ROPE_SCALING)) unscaled = _unsloth_rotary(_make_config(None)) @@ -397,7 +399,7 @@ def test_cos_cache_differs_between_scaled_and_unscaled_at_long_position(): ) -@requires_cuda +@requires_gpu def test_extended_cache_keeps_scaling_after_growth(): scaled = _unsloth_rotary(_make_config(LLAMA3_ROPE_SCALING)) # Grow past the initial cache size (mirrors long-context decode). @@ -456,7 +458,7 @@ def _build_longrope_rotary(): return rot, config -@requires_cuda +@requires_gpu @pytest.mark.parametrize( "build", [_build_llama3_rotary, _build_longrope_rotary], ids = ["llama3", "longrope"] ) diff --git a/unsloth/dataprep/raw_text.py b/unsloth/dataprep/raw_text.py index fdaba181f1..0920e2d7f4 100644 --- a/unsloth/dataprep/raw_text.py +++ b/unsloth/dataprep/raw_text.py @@ -216,19 +216,32 @@ class RawTextDataLoader: def _read_file_by_format(self, file_path, file_format): """Read file content based on detected format.""" - with open(file_path, "r", encoding = "utf-8") as f: + # utf-8-sig: Windows tooling (PowerShell's Out-File, Excel's "CSV UTF-8") prepends + # a BOM that plain utf-8 keeps as a leading character. Without a BOM it decodes + # exactly like utf-8. + with open(file_path, "r", encoding = "utf-8-sig") as f: if file_format == "plain_text" or file_format == "markdown": return f.read() elif file_format == "json_lines": - lines = [] - for line in f: + if Path(file_path).suffix.lower() == ".json": + # A .json file is a single JSON document (commonly a list + # of records), so parsing it per line drops the whole file. try: - data = json.loads(line.strip()) - text = self._extract_text_from_json(data) - if text: - lines.append(text) + parsed = json.load(f) + records = parsed if isinstance(parsed, list) else [parsed] except json.JSONDecodeError: - continue + # Some files carry JSON Lines under a .json name. + f.seek(0) + records = self._iter_json_lines(f) + else: + # A .jsonl file is one JSON value per line: stay streaming so + # a large file is never held in memory all at once. + records = self._iter_json_lines(f) + lines = [] + for data in records: + text = self._extract_text_from_json(data) + if text: + lines.append(text) return "\n\n".join(lines) elif file_format == "csv_text_column": reader = csv.DictReader(f) @@ -244,6 +257,17 @@ class RawTextDataLoader: _TEXT_FIELDS = ("text", "content", "message", "body", "description", "prompt") _TEXT_COLUMNS = _TEXT_FIELDS + def _iter_json_lines(self, handle): + """Yield one parsed JSON value per line, skipping blank and malformed lines.""" + for line in handle: + line = line.strip() + if not line: + continue + try: + yield json.loads(line) + except json.JSONDecodeError: + continue + def _extract_text_from_json(self, data): """Extract text from JSON object using common field names.""" # Skip non-object lines (str/list/number): `field in data` would be a diff --git a/unsloth/utils/attention_dispatch.py b/unsloth/utils/attention_dispatch.py index eda6103d5b..54f8100ca1 100644 --- a/unsloth/utils/attention_dispatch.py +++ b/unsloth/utils/attention_dispatch.py @@ -31,6 +31,8 @@ from ..utils.packing import ( build_xformers_block_causal_mask, ) +flash_attn_func = None +flash_attn_varlen_func = None if HAS_FLASH_ATTENTION: from flash_attn import flash_attn_func, flash_attn_varlen_func HAS_XFORMERS = xformers is not None diff --git a/unsloth_cli/commands/studio.py b/unsloth_cli/commands/studio.py index 7d0f8e4764..fa120422fc 100644 --- a/unsloth_cli/commands/studio.py +++ b/unsloth_cli/commands/studio.py @@ -1263,7 +1263,8 @@ def studio_default( max = _PARALLEL_MAX, help = ( f"llama-server parallel decode slots ({_PARALLEL_MIN}..{_PARALLEL_MAX}). " - f"Default {_PARALLEL_DEFAULT_PLAIN}." + f"Default {_PARALLEL_DEFAULT_PLAIN}. The Studio run settings " + "(Parallel Slots) override it per load." ), ), cloudflare: Optional[bool] = typer.Option( @@ -1880,7 +1881,8 @@ def run( help = ( "llama-server parallel decode slots. N requests share one " "loaded model; each slot gets ctx/N KV cache. Default " - f"{_PARALLEL_DEFAULT_RUN} (pre-PR hardcoded value)." + f"{_PARALLEL_DEFAULT_RUN} (pre-PR hardcoded value). The Studio " + "run settings (Parallel Slots) can override it per load." ), ), cloudflare: Optional[bool] = typer.Option(