Studio: re-validate matching existing installs and reused source builds (#5807)
A metadata match used to short-circuit straight to reuse, so a previously installed CPU-only 'GPU' binary survived every rerun and restart -- the exact 'picks CPU forever' report. install_prebuilt now smoke-tests a matching GPU install and reinstalls if it loads on CPU; setup.sh/setup.ps1 smoke-test a reused source build on a GPU host and rebuild if it ran on CPU. Non-GPU installs keep the fast path.
This commit is contained in:
danielhanchen
parent
ecf90078dd
commit
100e27ffe7
4 changed files with 190 additions and 10 deletions
|
|
@ -6704,6 +6704,44 @@ def validate_prebuilt_attempts(
|
|||
raise PrebuiltFallback("no prebuilt bundle passed validation")
|
||||
|
||||
|
||||
def existing_gpu_install_offloads(
|
||||
install_dir: Path,
|
||||
host: HostInfo,
|
||||
plan: InstallReleasePlan,
|
||||
probe_path: Path,
|
||||
) -> bool:
|
||||
"""For a GPU plan whose metadata matches the existing install, smoke-test
|
||||
the already-installed llama-server's offload before reusing it. Returns True
|
||||
to keep the existing install (non-GPU kind, passed, or inconclusive) and
|
||||
False on a definite CPU-only load so the caller reinstalls. This closes the
|
||||
"reinstall/restart keeps the silently CPU-only binary" path (#5807): without
|
||||
it, a metadata match short-circuits the new offload validation entirely."""
|
||||
choice = plan.attempts[0]
|
||||
if choice.install_kind not in _GPU_INSTALL_KINDS:
|
||||
return True
|
||||
server_name = "llama-server.exe" if host.is_windows else "llama-server"
|
||||
try:
|
||||
server_path = discover_installed_executable(install_dir, server_name)
|
||||
except PrebuiltFallback:
|
||||
return True
|
||||
try:
|
||||
validate_server(
|
||||
server_path,
|
||||
probe_path,
|
||||
host,
|
||||
install_dir,
|
||||
runtime_line = choice.runtime_line,
|
||||
install_kind = choice.install_kind,
|
||||
)
|
||||
except GpuOffloadFailure:
|
||||
return False
|
||||
except PrebuiltFallback:
|
||||
# Inconclusive (failed to start, etc.): keep the existing install rather
|
||||
# than reinstall on uncertain evidence.
|
||||
return True
|
||||
return True
|
||||
|
||||
|
||||
def install_prebuilt(
|
||||
install_dir: Path,
|
||||
llama_tag: str,
|
||||
|
|
@ -6747,8 +6785,12 @@ def install_prebuilt(
|
|||
published_repo,
|
||||
published_release_tag,
|
||||
)
|
||||
if release_plans and existing_install_matches_plan(
|
||||
install_dir, host, release_plans[0]
|
||||
# Non-GPU match: keep the fast path (no probe download). A GPU match
|
||||
# must still be smoke-tested below, so it does not short-circuit here.
|
||||
if (
|
||||
release_plans
|
||||
and existing_install_matches_plan(install_dir, host, release_plans[0])
|
||||
and release_plans[0].attempts[0].install_kind not in _GPU_INSTALL_KINDS
|
||||
):
|
||||
current = release_plans[0]
|
||||
log(
|
||||
|
|
@ -6765,9 +6807,27 @@ def install_prebuilt(
|
|||
release_count = len(release_plans)
|
||||
for release_index, plan in enumerate(release_plans):
|
||||
choice = plan.attempts[0]
|
||||
if existing_install_matches_plan(install_dir, host, plan):
|
||||
# A metadata match used to skip straight to reuse; now a
|
||||
# matching GPU install is smoke-tested first so a previously
|
||||
# installed CPU-only "GPU" binary is rebuilt instead of kept
|
||||
# forever across reruns/restarts (#5807).
|
||||
matched = existing_install_matches_plan(install_dir, host, plan)
|
||||
existing_install_dir: Path | None = install_dir
|
||||
if matched and not existing_gpu_install_offloads(
|
||||
install_dir, host, plan, probe_path
|
||||
):
|
||||
log(
|
||||
"existing llama.cpp install already matches fallback release "
|
||||
"existing GPU llama.cpp install served a completion but "
|
||||
"loaded the model on CPU; reinstalling to recover GPU "
|
||||
"offload (unslothai/unsloth#5807)"
|
||||
)
|
||||
matched = False
|
||||
# Don't let validate_prebuilt_attempts short-circuit on
|
||||
# the same bad install we just rejected.
|
||||
existing_install_dir = None
|
||||
if matched:
|
||||
log(
|
||||
"existing llama.cpp install already matches release "
|
||||
f"{plan.release_tag} upstream_tag={plan.llama_tag}; skipping reinstall"
|
||||
)
|
||||
return
|
||||
|
|
@ -6788,7 +6848,7 @@ def install_prebuilt(
|
|||
release_tag = plan.release_tag,
|
||||
approved_checksums = plan.approved_checksums,
|
||||
initial_fallback_used = release_index > 0,
|
||||
existing_install_dir = install_dir,
|
||||
existing_install_dir = existing_install_dir,
|
||||
)
|
||||
except ExistingInstallSatisfied:
|
||||
return
|
||||
|
|
|
|||
|
|
@ -2633,6 +2633,16 @@ if (Test-Path -LiteralPath $LlamaServerBin) {
|
|||
Write-Host " Existing llama-server was built with CUDA but no GPU detected -- rebuilding" -ForegroundColor Yellow
|
||||
$NeedRebuild = $true
|
||||
}
|
||||
# The cache check catches a CPU build on a GPU host; this catches a CUDA
|
||||
# build that still loads on CPU at runtime (PTX / runtime-init failure,
|
||||
# #5807). Smoke-test before reusing it on a GPU host.
|
||||
if (-not $NeedRebuild -and $HasNvidiaSmi -and $cachedCuda) {
|
||||
& python "$PSScriptRoot\install_llama_prebuilt.py" --smoke-test "$LlamaServerBin" --install-dir "$LlamaCppDir" --install-kind "windows-cuda" 2>&1 | Out-String | Write-Host
|
||||
if ($LASTEXITCODE -eq 2) {
|
||||
Write-Host " Existing CUDA llama-server runs on CPU only -- rebuilding" -ForegroundColor Yellow
|
||||
$NeedRebuild = $true
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
|
|
|
|||
|
|
@ -919,12 +919,41 @@ if [ "$_NEED_LLAMA_SOURCE_BUILD" = true ] && \
|
|||
[ -z "$_LLAMA_PR" ] && \
|
||||
[ -x "$LLAMA_CPP_DIR/build/bin/llama-server" ] && \
|
||||
[ -x "$LLAMA_CPP_DIR/build/bin/llama-quantize" ]; then
|
||||
step "llama.cpp" "existing source build found; skipping rebuild"
|
||||
ln -sf build/bin/llama-quantize "$LLAMA_CPP_DIR/llama-quantize"
|
||||
if [ "$_STUDIO_HOME_IS_CUSTOM" = true ]; then
|
||||
: > "$LLAMA_CPP_DIR/$_STUDIO_OWNED_MARKER" 2>/dev/null || true
|
||||
_REUSE_SOURCE=true
|
||||
# On a GPU host, smoke-test the existing source binary first so a stale
|
||||
# CPU-only build (e.g. an earlier no-toolkit fallback) is rebuilt instead of
|
||||
# silently reused on a GPU host (#5807). Exit 2 = ran on CPU -> rebuild;
|
||||
# anything else keeps the build (never downgrade on uncertain evidence).
|
||||
_REUSE_KIND=""
|
||||
if [ "$_HOST_SYSTEM" = "Darwin" ] && { [ "$_HOST_MACHINE" = "arm64" ] || [ "$_HOST_MACHINE" = "aarch64" ]; }; then
|
||||
_REUSE_KIND="macos-arm64"
|
||||
elif command -v nvidia-smi >/dev/null 2>&1; then
|
||||
_REUSE_KIND="linux-cuda"
|
||||
elif [ "$_LINUX_HAS_GPU" = true ]; then
|
||||
_REUSE_KIND="linux-rocm"
|
||||
fi
|
||||
if [ -n "$_REUSE_KIND" ]; then
|
||||
if python "$SCRIPT_DIR/install_llama_prebuilt.py" \
|
||||
--smoke-test "$LLAMA_CPP_DIR/build/bin/llama-server" \
|
||||
--install-dir "$LLAMA_CPP_DIR" \
|
||||
--install-kind "$_REUSE_KIND" > "$LLAMA_CPP_DIR/gpu-smoke-existing.log" 2>&1; then
|
||||
_REUSE_RC=0
|
||||
else
|
||||
_REUSE_RC=$?
|
||||
fi
|
||||
if [ "$_REUSE_RC" -eq 2 ]; then
|
||||
substep "existing source build runs on CPU only; rebuilding for GPU..." "$C_WARN"
|
||||
_REUSE_SOURCE=false
|
||||
fi
|
||||
fi
|
||||
if [ "$_REUSE_SOURCE" = true ]; then
|
||||
step "llama.cpp" "existing source build found; skipping rebuild"
|
||||
ln -sf build/bin/llama-quantize "$LLAMA_CPP_DIR/llama-quantize"
|
||||
if [ "$_STUDIO_HOME_IS_CUSTOM" = true ]; then
|
||||
: > "$LLAMA_CPP_DIR/$_STUDIO_OWNED_MARKER" 2>/dev/null || true
|
||||
fi
|
||||
_NEED_LLAMA_SOURCE_BUILD=false
|
||||
fi
|
||||
_NEED_LLAMA_SOURCE_BUILD=false
|
||||
fi
|
||||
|
||||
# ── 8. WSL: pre-install GGUF build dependencies for fallback source builds ──
|
||||
|
|
|
|||
|
|
@ -499,3 +499,84 @@ def test_main_smoke_exit_error_on_inconclusive(monkeypatch):
|
|||
|
||||
rc = _run_main_smoke(monkeypatch, impl)
|
||||
assert rc == M.EXIT_ERROR # 1 -> setup scripts keep the GPU build
|
||||
|
||||
|
||||
# -- 6. existing_gpu_install_offloads: re-validate a matching install (#5807) --
|
||||
|
||||
|
||||
def _gpu_plan(install_kind = "linux-cuda"):
|
||||
choice = M.AssetChoice(
|
||||
repo = "unslothai/llama.cpp",
|
||||
tag = "b9001",
|
||||
name = "app-b9001-linux-x64-cuda13-newer.tar.gz",
|
||||
url = "https://example.com/x",
|
||||
source_label = "published",
|
||||
install_kind = install_kind,
|
||||
)
|
||||
return M.InstallReleasePlan(
|
||||
requested_tag = "latest",
|
||||
llama_tag = "b9001",
|
||||
release_tag = "rel",
|
||||
attempts = [choice],
|
||||
approved_checksums = M.ApprovedReleaseChecksums(
|
||||
repo = "unslothai/llama.cpp", release_tag = "rel", upstream_tag = "b9001",
|
||||
artifacts = {},
|
||||
),
|
||||
)
|
||||
|
||||
|
||||
def _with_server(tmp_path):
|
||||
server = tmp_path / "llama-server"
|
||||
server.write_text("#!/bin/sh\n")
|
||||
probe = tmp_path / "probe.gguf"
|
||||
probe.write_bytes(b"GGUF")
|
||||
return probe
|
||||
|
||||
|
||||
def test_existing_cpu_kind_install_is_kept(tmp_path):
|
||||
# A non-GPU existing install is never offload-gated.
|
||||
probe = _with_server(tmp_path)
|
||||
assert M.existing_gpu_install_offloads(
|
||||
tmp_path, nvidia_host(), _gpu_plan("linux-cpu"), probe
|
||||
) is True
|
||||
|
||||
|
||||
def test_existing_gpu_install_cpu_only_triggers_reinstall(monkeypatch, tmp_path):
|
||||
probe = _with_server(tmp_path)
|
||||
|
||||
def fake_validate(*a, **k):
|
||||
raise M.GpuOffloadFailure("loaded the model entirely on CPU")
|
||||
|
||||
monkeypatch.setattr(M, "validate_server", fake_validate)
|
||||
assert M.existing_gpu_install_offloads(
|
||||
tmp_path, nvidia_host(), _gpu_plan("linux-cuda"), probe
|
||||
) is False
|
||||
|
||||
|
||||
def test_existing_gpu_install_offloading_is_kept(monkeypatch, tmp_path):
|
||||
probe = _with_server(tmp_path)
|
||||
monkeypatch.setattr(M, "validate_server", lambda *a, **k: None)
|
||||
assert M.existing_gpu_install_offloads(
|
||||
tmp_path, nvidia_host(), _gpu_plan("linux-cuda"), probe
|
||||
) is True
|
||||
|
||||
|
||||
def test_existing_gpu_install_inconclusive_is_kept(monkeypatch, tmp_path):
|
||||
probe = _with_server(tmp_path)
|
||||
|
||||
def fake_validate(*a, **k):
|
||||
raise PrebuiltFallback("llama-server exited during startup")
|
||||
|
||||
monkeypatch.setattr(M, "validate_server", fake_validate)
|
||||
assert M.existing_gpu_install_offloads(
|
||||
tmp_path, nvidia_host(), _gpu_plan("linux-cuda"), probe
|
||||
) is True
|
||||
|
||||
|
||||
def test_existing_gpu_install_no_binary_is_kept(tmp_path):
|
||||
# No llama-server present -> let the normal flow reinstall, don't crash.
|
||||
probe = tmp_path / "probe.gguf"
|
||||
probe.write_bytes(b"GGUF")
|
||||
assert M.existing_gpu_install_offloads(
|
||||
tmp_path, nvidia_host(), _gpu_plan("linux-cuda"), probe
|
||||
) is True
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue