- The cached-model listing tagged any repo with a model_index.json as
text-to-image, so a community pipeline the image loader's trust rule refuses
still got a row in the Images picker, and a detected-but-untrusted video repo
fell through to that same tag. Gate the image tag on the load path's rule and
hide an untrusted video repo outright.
- A routed diffusion pick only carries a GGUF filename, which is all the chat
picker has, so a curated single-file artifact arrived with no quant and was
loaded as a pipeline: from_pretrained on a repo with no model_index.json. Pass
the page's own catalog spec into the route pick, so a routed pick resolves to
exactly what a direct pick on that page resolves to.
- The dataset mutation endpoints checked is_active() and only then handed their
filesystem work to a thread, so a start reserving in that gap changed captions
or removed images underneath the preflight or the running trainer. The
interlock is now registered for the whole request under the lock reserve()
uses, and a start refuses while a mutation is open rather than waiting on it.
- GIF export held every kept frame as a paletted image before encoding; a clip
may be 2048x2048 for 1024 frames, and at the 12 fps target the step is 1, so
one export click could allocate over 4 GB and take the backend down. Downscale
past 720 px and widen the step to keep at most 300 frames.
- seed accepted any Python int, so an out-of-range one passed every preflight,
evicted the resident models, spawned the trainer and only then died in
torch.manual_seed. Bound it to torch's 64-bit range in the request and config.
Comment-only pass over the Python this PR touches: drop what the code already
says, collapse multi-line explanations that still read on one line, and keep
the reasoning that is not recoverable from the code. No code, docstring
semantics or behaviour changes; verified with an AST comparison against the
previous revision, and the backend suite is unchanged (same 37 environment
failures as before: the API integration tests that need a live keyed server,
the flash-attn install hooks, and the GPU memory fields).
Four fixes from the latest review round:
- The GPU arbiter's chat evictor only cancelled the llama.cpp side. The
orchestrator publishes active_model_name once its worker reports success, so
an in-flight safetensors load was visible only as an entry in loading_models
and finished onto the GPU after ownership had transferred. Cancel every
pending load, and give the safetensors branch the post-load ownership recheck
the GGUF branch already had.
- A manual gpu_layers=0 GGUF load runs on the CPU with the GPUs hidden from the
child, yet it took the arbiter unconditionally: it cancelled a running image
or video generation for a model needing no VRAM, then held CHAT ownership so
the next GPU workload unloaded it for nothing. Gate the acquire on the same
predicate the launch-time CPU-only mask uses, as the image and video loaders
gate on their resolved device.
- The staged-download hook subscribes per repo, not per job, so another job on
the same repo advanced the staged queue (starting a load whose scoped files
were still downloading) or wiped a queue that was still running. Compare the
variant each callback carries, like the chat page's auto-load does.
- The video gallery fetched every record of a page into an object URL that
lives until the page closes: 50 clips at tens to hundreds of MB each, for
cards the user may never scroll to. Fetch a clip as its card nears the strip's
edge, plus the selected one the player needs.
Three from the latest review.
The video download plan always asked for the wide base file list, so an LTX-2.3
pick staged the 2.0 base's VAEs, vocoder and connectors that the checkpoint
supplies itself, while the companion files the 2.3 assembly does read were left
out of the plan and pulled inline at load, outside the panel's progress, cancel
and disk preflight. The plan now recognises a 2.3 pick by name (the load keeps
the authoritative header probe, and under-guessing only falls back to the
load-time pull), narrows the base list, and stages the extras in the same entry
as the checkpoint so one repo stays one scoped job.
A pick routed from the chat picker arrives as ?model= and ?quant= with no picker
metadata, so a bare local .gguf or .safetensors was loaded as a pipeline: an
explicit model_kind wins over the backend's filename sniffing, so it evicted the
resident model and then failed on the missing model_index.json. Both pages now
derive the load kind from the path, the same way their own picker handlers do.
A torchao int8/fp8 build takes adapters only at load time. Switching artifact
inside one family keeps the LoRA selection, since the family did not change,
but the load did not bake it, so the next generation was rejected with 'reload
the model with the adapter selection' while the picker still showed the adapter
as active. The selection is now dropped once per resident build, with a message
saying to pick and load again.
Six review findings, three of them evict-then-fail orderings:
- The chat load reclaimed the GPU without telling the arbiter it existed. A
chat load holds no llama-server process until its GGUF has downloaded,
which is minutes, so a competing Images/Video acquire in that window
found nothing to cancel, took the GPU, and the chat load then spawned
onto the same device. It now registers an in-flight marker through
acquire_for's register hook (under the arbiter lock, as the image and
video loads do), the evictor cancels a marked load, and the route undoes
itself if ownership moved while it loaded.
- The Hub-download conflict check ran after that handoff, so a GGUF the
download manager already owns destroyed the resident Images/Video
pipeline and then 409'd, having loaded nothing. It moves above the
handoff, together with the marker it handshakes with.
- The image load released the engine router's transition lock before
registering the load, so a second load choosing the other engine could
unload the still-idle engine this one captured; the load then landed on a
deactivated engine, where generate, status, unload and the arbiter's
evictor can no longer reach it. Registration now happens under that lock
and refuses if the engine changed.
- Training a DiT family on a host with no GPU was accepted: nf4 is not a
CPU fallback, its 4-bit load goes through bitsandbytes, which requires
CUDA, XPU or MPS. The start unloaded the working Images pipeline, pulled
the text encoders, and only then died in the child. Rejected before the
teardown now, and /info stops advertising a precision that always 400s.
SDXL keeps its documented fp32-on-CPU path.
- Both diffusion pages kept the routed-pick marker forever, so re-picking
the same checkpoint (after chat evicted it) neither loaded nor cleared
the query string. The marker is released once the query is gone. The
Images key also carried a stray NUL byte, which made the file read as
binary to grep and other tooling.
- diffusers dropped Python 3.9 in 0.38, so the unconditional >=0.39.0 pin
left pip no candidate at all on 3.9 and made every install that composes
the huggingface extras unresolvable there. The floor is conditional now.
Also fixes tests that were already red on the branch: two hand-built
request fakes had gone stale against fields this branch added, and the
handoff-ordering test only failed on a host with fewer than two GPUs.
Resolves the app-sidebar conflict: main added Hub and Projects rows
inline while this branch renders the nav from navRows in the order and
pin state set under Settings -> Appearance. Kept the data-driven
rendering, having checked both of main's additions are already
represented there - the projects row carries the same icon, label,
active check, handlers and inline New project button.
Main also replaced the sidebar's inline name field with
NewProjectDialog, which owns its own state, so the button no longer
resets a name draft: it sets the move target and opens the dialog, as
main's other call sites do.
They downloaded inline inside the load, so they had none of the manager's disk
preflight, manifest verification, resume or panel progress. Picks now stage as
scoped jobs carrying the loader's own file list, then load from a warm cache.
Reports the repos and exact files a pick needs so the download manager can stage
them with the loader's own file scope. A plain snapshot would add the packaged
root single, transformer shards and fp16 twins the loader never opens.
Both read huggingface_hub's import-time HF_HUB_CACHE, which changing the cache
folder does not update: progress counted the old root while the download wrote to
the new one, and from_pretrained could split one model across both.
* Fix GGUF tool chat server recovery
* [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
* Cover MTP precedence and loosen the replay assertion for PR #7424
Add a regression test for the MTP branch of the tool-loop respawn retry: the
file-wide _make_backend stub forces _maybe_recover_from_mtp_crash to False, so
nothing exercised the case where an MTP crash reload is already claimed and an
ordinary same-config respawn must not run on top of it. Cover both the next
tool-loop request and the final synthesis pass.
Replace the whole-payload equality assertions with a field-wise check. Comparing
the full dict pins max_tokens to the value derived from the dead server's
effective context, so a later fix that rebuilds server-derived defaults after a
respawn would read as a test failure rather than an improvement.
Document that the one-retry budget is per model request, not per chat turn.
* Recover from prefill-time deaths and stop respawn racing the MTP reload
Two gaps in the tool-loop respawn retry, both reproduced before fixing.
A child that exits during prefill has already accepted the socket, so httpx
raises ReadError, WriteError or RemoteProtocolError rather than ConnectError.
Those all arrive before the response opens, which is exactly the window where a
replay is safe, but the helper only caught ConnectError and gave up. Widen the
catch to NetworkError plus RemoteProtocolError. Timeouts stay excluded on
purpose: they mean the server is slow, not dead, and retrying one would spend
the 20 minute first-token budget twice. Windows resets connections where Linux
refuses them, so this also covers the common Windows presentation.
_maybe_recover_from_mtp_crash returns False both when the crash is not an MTP
crash and when an MTP-free reload is already in flight. Callers read that as
permission to respawn, so _respawn_if_dead replayed the crashing MTP kwargs and,
by replacing the process, made the in-flight reload abort on its own newer-load
check. Skip the respawn while that reload owns the corpse. The guard lives in
_respawn_if_dead so the plain chat path gets it too.
Regression tests for both, including a guard against retrying prefill timeouts.
* Release the MTP single-flight claim when the reload never starts
_mtp_runtime_fallback_in_progress is claimed before the reload thread exists, and
only that thread's finally clears it. Two statements ran in between with no unwind
path: re-reading _last_load_kwargs, which an unload can null underneath us, and
Thread.start(), which raises under the thread exhaustion that is exactly the
pressure killing llama-server in the first place. Nothing else ever resets the
flag, so a failure there latched it for the life of the process.
That was survivable before, since respawn ignored the flag. It is not now: the
guard added in db78184be keys off the flag alone, so a latch would silently
disable auto-respawn for every later model, including plain non-MTP ones. Read
the kwargs and process once before claiming, and release the claim if the thread
cannot start.
Restore the whole-payload equality assertions. Comparing field-wise was meant to
leave room for rebuilding server-derived defaults on replay, but the payload is
built once before the retry and re-sent unchanged, so the looser check only
dropped seven real keys and added a vacuous seed comparison.
Also correct the docstring: llama-server flushes its 200 at slot start, so a
death during decode arrives with the response already open. The pre-header window
this covers is an upload still in flight or a request waiting behind busy slots.
* Confirm the child exited before spending the retry
A closing llama-server can beat its own exit status: the socket error arrives while
poll() still reports the process running. _respawn_if_dead then took the alive
branch, handed back the stale _healthy, and the caller read that as a successful
respawn and spent its single retry on the same corpse. When that retry failed,
attempt was no longer 0, so no respawn ever happened and the turn died, with a log
line claiming a respawn that had not occurred. The window matters most for the
pre-header ReadError and RemoteProtocolError shutdowns the retry now covers.
Wait a bounded second for the exit status before calling the child alive. The same
race is already conceded in _maybe_recover_from_mtp_crash, whose recovery thread
polls for 5s because the error can arrive a beat early; 1s here because this runs
on the request path, and a genuinely live server, including one a concurrent caller
has just respawned, still returns promptly.
* Tighten the recovery comments
* Harden the respawn path around concurrent unloads and replacements
Two problems with the reap grace loop, both found by review.
Skip the grace when the server was already replaced. A caller queued on
_respawn_lock behind someone else's respawn woke holding the healthy replacement,
could not tell it from the child its own request had used, and waited out the full
grace. That sleep is under the lock, so the waits serialised: four concurrent
generations cost roughly three grace periods before any retry began. Capture the
process before taking the lock and return early once it has been swapped.
Do not respawn a server that is being torn down on purpose. unload_model() sets
_cancel_event and only clears _last_load_kwargs after the kill, so a request losing
its connection mid-unload could watch that deliberate exit through the grace loop,
read the stale kwargs and load the model straight back; a model switch landing
during the wait was reverted the same way. Re-check the cancel flag and the process
identity under _serial_load_lock before capturing the replay kwargs, matching what
the MTP-crash reload already does.
* [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
* Tighten the respawn comments
* Do not charge the reap grace to a server that is still serving
The grace loop added for the not-yet-reaped race waits on poll(), which for a
live child never returns, so every transient transport error paid the full
_RESPAWN_REAP_GRACE_S. That sleep is held under _respawn_lock, so the cost
serialised: measured 1002 ms for one caller and 8.02 s for eight concurrent ones,
against 0 ms on main. A working install pays this, not a broken one.
A llama-server's listening socket dies with the process, so a loopback connect
separates the two cases in microseconds. Probe it first and return immediately
when the port still accepts; fall through to the grace only when the port is
gone, which is the case the grace exists for. Back to 0.7 ms for one caller and
0.00 s for eight.
Cross-checked on real hardware over Qwen3.5-2B, Llama-3.2-1B, Gemma-3-4B with
mmproj and Qwen3-30B-A3B: decode throughput within noise of main (-0.06%, -3.71%,
+2.57%, +0.29%, against a 54-232% spread between rounds of a single run), output
byte-identical on every round, tool-path recovery restored on the three families
whose model calls the tool, and plain-chat recovery still working on all four.
* [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
* Make the respawn lose to a deliberate unload in every window
Two follow-ups on the respawn path, both reproduced first.
Check _cancel_event before the socket fast path. unload_model sets the flag before
it kills, so the child is still accepting when the probe runs; returning the stale
_healthy there aims the retry at a server that is deliberately going away.
Close the unload TOCTOU. The old cancel check sat under _serial_load_lock, which
unload_model never takes, so an unload could land entirely between that check and
load_model and the captured kwargs would restart a model the user had stopped.
Snapshot the kwargs, the flag and a new _unload_epoch together under _lock, the
lock unload does hold, so a teardown is either wholly before the snapshot or
wholly after it. load_model clears _cancel_event on the way in, so the epoch is
the only evidence that survives; when it moves during the reload the replacement
is unloaded again rather than left running.
_lock stays uncontended across load_model, which would deadlock a plain Lock and
block /status for the length of a load. Error-path latency is unchanged: 0.6 ms
for a live server and 0.00 s for eight concurrent callers.
---------
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
Co-authored-by: danielhanchen <unslothai@gmail.com>
Co-authored-by: danielhanchen <danielhanchen@gmail.com>
- The trainer keyed its persistent conditioning cache on family and
resolution only, while the keys themselves carry just the caption or
image content and crop variant. One cache directory reused for two
checkpoints, or for the same repo at a new revision, let a warm run
skip loading its encoders and train on the other model's embeddings
and latent statistics. Namespace on the base checkpoint and its
resolved revision as well. The revision helper now lives beside the
cache in diffusion_train_extras and the inference wrapper delegates to
it, so the two cannot disagree about what counts as the same source.
- The diffusion learning rate only checked positivity, but 1e309 floats
to inf and satisfies gt, so the route evicted the resident models and
started AdamW with an infinite rate: the first step destroys the
adapter while progress looks normal and the result is saved. Bound it
below 1.0, matching the LLM schema, which rejects inf for the same
reason.
Two correctness fixes:
- The cache keyed the checkpoint and its companion base by name only, so
a Hub repo advancing to a new commit, or a local directory updated in
place, kept returning embeddings from the previous text encoder. Pair
both with a revision marker: the locally resolved commit sha for a Hub
repo, config plus text-encoder file stats for a directory. Neither
loads the encoders, so a warm run still keeps them off the GPU.
- flow_shift only checked positivity, but JSON accepts 1e309, which
floats to inf, and inf <= 0 is False while NaN fails every comparison.
The sigma table then evaluates s * u / (1 + (s - 1) * u) as NaN, which
poisons every sampled sigma and saves a corrupted adapter while
progress looks normal. Require a finite value.
Six review findings across the Images page and model scanning:
- The quantized (int8/fp8) load path can only attach LoRA adapters
before quantization, but the frontend load request had no loras field,
so every generation after such a load was rejected and each reload
repeated it. Send the selection with the load.
- build_prequant_checkpoint passed no family to the scheme exclusions
while recording the family in metadata, so a Qwen int8 artifact baked
the short-M text-stream linears and was then rejected wholesale by the
loader's family-keyed check.
- Registering a bare single-file checkpoint directory produced no On
Device row even though the images loader can load it; only its parent
worked. Admit that shape when nothing else matched.
- Unload left the Reapply target set, so the repair path was skipped and
Reapply reloaded the ejected model. Clear it, as the video page does.
- Both FLUX.2 bases were trusted for training but not inference, so
Deploy to Create rejected every FLUX.2 adapter.
- Outpaint allocated the grown canvas before downscaling, exceeding the
browser canvas area cap on a large photo; an over-cap canvas is
unusable, so Extend silently posted a fully transparent image and
mask. Scale the source first.
Four bugs in the batched inference path, all found by review:
- A mixed-prompt batch sent a scalar negative prompt against a prompt
list. Z-Image asserts on the length, and Qwen-Image, Krea 2 and FLUX
true-CFG encode a batch-1 negative against batch-N latents and fail in
the transformer's text/image concat. Broadcast it to match the batch.
- The FBCache step-cache reset sat above the chunk loop. diffusers only
resets that state at the end of a successful call, so a forward that
raised (the OOM the backoff is meant to recover) left its own residual
behind and the halved retry died on a shape mismatch. Reset before
every forward instead.
- The conditioning cache keyed on the checkpoint alone, but a GGUF or
single-file load takes its text encoders from the companion base, so
the same checkpoint against a different base reused the previous
base's embeddings. Key the base too.
- Gallery records stored the base seed and the requested batch size even
when a prompts/seeds list drove the run, so restoring the second image
of seeds=[5, 99] replayed seed 5. List-driven outputs now record as
single-image recipes on their own seed.
Also bound strength above 0: every img2img pipeline derives its step
count from it, so 0 leaves zero denoising steps and either raises or, on
SDXL, crashes on empty latents.
read_text raises UnicodeDecodeError, which is not an OSError, so one bad caption
sidecar or video sidecar 500d the info, upload and gallery routes. A flat image
now yields the all-black edge map instead of its own luminance, and the four DiT
loss knobs the trainer implements are declared so model_dump keeps them.
* fix(studio): support hostname-based enterprise proxies
* [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
* fix(studio): strip userinfo from proxy fetch targets
---------
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
Co-authored-by: Lee Jackson <130007945+Imagineer99@users.noreply.github.com>
* ROCm/AMD CI coverage: arch-table parity, native-Linux lib prepend, RDNA4 grouped_mm, discovery-based shell suite
Three merged ROCm fixes shipped without tests, and the CI wiring that
would have run them was gated on files the fixes do not touch.
Tests added (113):
tests/studio/install/test_rocm_arch_table_parity.py (27)
diffs the four duplicated gfx -> AMD pip-index tables across
install.sh, install.ps1, studio/setup.ps1 and install_python_stack.py,
plus the GPU-name -> arch tables and the torch 2.11 pin allowlist.
tests/studio/install/test_rocm_native_linux_lib_dirs.py (26)
covers #7233: system-ROCm lib dirs prepended ahead of bundled
libggml-hip, the /dev/kfd + not-WSL + libhsa gate, the opt-out env
var, root resolution order, and source parity between the two copies.
studio/backend/tests/test_grouped_mm_rdna4_fallback.py (46)
covers #7292: registration on the CUDA dispatch key, grouped and
ungrouped numerics, bias/dtype promotion, and the Linux HIP<7.13 +
RDNA4 name gate, executed from the shipped source rather than a copy.
tests/studio/test_ci_shell_suite_coverage.py (14)
fails if either shell runner goes back to a hardcoded list or skips
a file without a recorded reason.
CI wiring:
studio-backend-ci.yml: add install.sh / install.ps1 to the path filter
(the suites it runs assert against those two files, so install-only
changes -- the shape most AMD/ROCm routing fixes take -- skipped it),
and replace the 13-file hardcoded shell list with directory
discovery. That list had fallen seven files behind, including
test_strixhalo_wsl_reroute.sh, the only shell coverage of the ROCm
WSL reroute, which had never run on a PR.
tests/run_all.sh: same discovery loop so local and CI agree.
* Test review fixes: assert on outcomes, not on the code under test
Self-review of the previous commit found four tests that passed for the
wrong reason.
1. The arch-table parity test pinned expected gfx ids copied out of the
shipped tables, which enshrined three upstream inaccuracies as
correct: RX 9070 (non-XT) is gfx1201 not gfx1200, RX 7800 XT is
gfx1101 not gfx1100, and PRO V710 is gfx1101 not gfx1102 per AMD's
ROCm compatibility matrix. The expectation is now the AMD pip index
leaf -- the thing the tables exist to produce, and what a wrong
answer costs the user. The three known drifts are listed explicitly
with a test asserting they stay cosmetic, i.e. that the wrong and
right ids still map to the same wheel index. That test turns red the
day one of them starts routing users to the wrong wheel.
2. The RDNA4 device-name test extracted the regex from worker.py and
then matched with it, so it could not fail. Widening the pattern --
the dangerous edit, since it forces the slow Python mm fallback onto
RDNA3 users -- would have been silently accepted. It now reads the
live pattern and checks it against fixed cases, plus asserts the
name match stays guarded by `not _lin_arch` and that the name is
lowercased before matching.
3. The CI-coverage test matched a verbatim line of studio-backend-ci.yml,
so reindenting the step would fail the build while a real regression
to a hardcoded list could slip past a reformat. It now parses the
YAML, finds the step by name, and asserts on the glob plus the
absence of individual filenames. The path-filter test likewise reads
the parsed trigger instead of scanning raw text.
4. A set comprehension in the parity helper had a ternary whose branches
were identical.
Mutation-tested: widening the RDNA4 regex, desyncing one copy of the
name table, dropping install.sh from the path filter, and re-skipping
the ROCm WSL shell suite each fail at least two tests. Verified on
Linux (WSL Ubuntu 24.04) with CI's torch pin: 86 + 48 pass.
* Fix three wrong gfx ids in the GPU-name arch tables
The name -> gfx tables disagreed with AMD's ROCm compatibility matrix on
three entries. Corrected against the "Radeon GPU" list at
rocm.docs.amd.com/en/latest/compatibility/compatibility-matrix.html:
RX 9070, RX 9070 GRE gfx1200 -> gfx1201 (Navi 48, same die as the XT)
RX 7800 XT, RX 7700 XT gfx1100 -> gfx1101 (Navi 32, not Navi 31)
PRO W7700 gfx1100 -> gfx1101
PRO V710 gfx1102 -> gfx1101 (Navi 32, not Navi 33)
No wheel changes for anyone: gfx1200/gfx1201 both resolve to gfx120X-all
and gfx1100/gfx1101/gfx1102 all resolve to gfx110X-all, in all four copies
of the index-family map. That collapse is why the errors survived being
copied into six places -- the leaf-level tests could not see them.
It was not purely cosmetic, though. install.sh's second copy feeds
"Tip: set UNSLOTH_ROCM_GFX_ARCH=<arch>", so a 7800 XT user following the
printed advice exported gfx1100 and made a wrong id authoritative for
every later run. It would also have become a real misroute the moment AMD
split a family across index leaves, as they already do for gfx1151/gfx1150.
Fixed in all six places, which is two more than the table's own "kept in
sync with" comments claim exist:
install.sh _infer_amd_gfx_arch_from_gpu_name
install.sh case "$_gpu_disp_mkt" (banner + env tip; undocumented)
studio/setup.sh
install.ps1
studio/setup.ps1
studio/install_python_stack.py
Ordering is preserved: the gfx1102 arm still precedes gfx1101 in the shell
copies so "RX 7700S" cannot fall onto the "RX 7700" glob, and the
PowerShell copies keep the (?!S) lookahead.
Test changes:
- test_rocm_arch_table_parity.py gains _AMD_DOCUMENTED_ARCH, exact gfx
ids transcribed from AMD rather than from the tables. Agreement between
six copies proves nothing when all six were transcribed from the same
mistake, so the ground truth has to come from outside. Verified it
catches the bug: against the pre-fix tables it fails 6 tests.
- The parity check now covers all six copies. It had four; the two
install.sh copies were being treated as one, and
_WIN_GPU_NAME_ARCH_TABLE was not checked at all.
- test_rocm_support.py's TestGfxArchNameFallback pinned two of the wrong
ids as expected values; updated, and extended with a 9060 XT and a
7900 XTX case so each RDNA3/4 die is represented.
* [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
* Guard against unregistered copies of the GPU-name arch table
Counting the copies by hand is what let them drift: the in-code "kept in
sync with" comments claimed four, the arch-id fix found six, and scanning
the tree turns up a seventh.
TestNoUnregisteredArchTable rediscovers the copies from the source tree
instead of trusting a hand-maintained list. A table line is one that names
a card and gives its arch; real tables score 9-17 such lines and the only
other hits in the repo are two single-line prose comments, so the
three-line threshold is not load-bearing. A companion test asserts the
scan still finds the known copies, so the heuristic cannot go blind and
pass by finding nothing.
The seventh copy is tests/_zoo_rocm_spoof.py, the fixture other ROCm tests
build their fake AMD host from. It states the mapping backwards (gfx ->
the name torch should report), which makes it an independent witness: it
had gfx1101 -> RX 7800 XT and gfx1201 -> RX 9070 XT right while all six
installer copies were wrong, and nothing compared the two. Now they are
round-tripped against each other.
RX 6700 XT is pinned as a known divergence rather than normalised. AMD's
compatibility matrix documents no consumer RX 6000 card and no gfx1031 at
all, the installer arm is commented "gfx103X family", and gfx1031 appears
only as an index-family key, never as a value a name table emits. With no
external source to correct against, changing shipped behaviour would be
guesswork. A test fails if the divergence ever disappears, so the
exemption cannot go stale.
Also adds the reverse of the AMD-matrix check: a documented card that
matches no arm anywhere is a silent CPU fallback rather than a wrong id.
This cannot detect hardware nobody transcribed, which would need a live
fetch of AMD's matrix and a non-hermetic suite; the docstring says so
rather than implying coverage that is not there.
Verified on Linux: 478 passed, plus all five new guards mutation-tested
to confirm each fails when its invariant is broken.
* [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
* Docstring said six copies; the list under it now has seven
* tests: run discovered shell tests with bash, not sh
tests/run_all.sh discovered tests/sh/ instead of listing files, but still
invoked each one with sh. Every file there declares a bash shebang, and on
Debian/Ubuntu /bin/sh is dash: test_apt_distro_prompt.sh,
test_studio_home_node_dir.sh and test_with_llama_cpp_dir_link_behavior.sh
fail on bashisms under dash and pass under bash. The old hand-written list
happened to name only dash-clean files, so switching to discovery is what
surfaced it. Backend CI already used bash, so this was a local-only break.
Guarded by a new test asserting both runners invoke tests/sh/ with bash.
* [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
* Fix Krackan Point (Radeon 860M/840M) routed to the gfx1150 wheel index
The GPU-name tables map 860M/840M and the Ryzen AI 7 350 / AI 5 340 CPU
strings to gfx1150, but Krackan Point is gfx1152. AMD's own lemonade table
(src/cpp/server/system_info.cpp) maps both Krackan iGPUs to gfx1152.
Unlike the three ids already fixed here, this one is not wheel-neutral:
repo.amd.com publishes gfx1150 and gfx1152 as separate index leaves with
separately built torch wheels, so these laptops were installing wheels
built for a different LLVM target. gfx1152 was absent from the codebase
entirely, so it needed the index-family maps, the torch 2.11 floor lists
(same _grouped_mm bug as gfx1150/1151), the Strix reroute set and the
Windows arch allowlist as well as the seven name tables.
The parity test added in this PR did not catch it because its AMD-matrix
expectations stopped at 890M/880M. Added the APU rows, so the case that
actually changes a wheel is now covered: reverting the tables fails 9
tests naming 860M, 840M and Krackan.
gfx1153 (Ryzen AI 5 430 era) is left alone; AMD publishes no gfx1153
wheel family, so there is nothing to route it to.
Verified: bash -n on both shell installers, PowerShell AST parse on both
.ps1 files, python ast.parse on all touched modules, install suite 1334
passed with no new failures against main, shell suite 20 files.
* [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
* Add gfx1152 to unified-memory classifiers, make parity allowlist set-based
Krackan Point (gfx1152, Radeon 860M/840M) is the third RDNA 3.5 APU and
shares one GPU/system-RAM pool exactly like Strix Point (gfx1150) and
Strix Halo (gfx1151), but only the installers knew about it. The two
runtime classifiers still had two-element arch sets, so a Krackan laptop
got the 0.90 discrete headroom factor on a shared pool and ran llama.cpp
without GGML_CUDA_ENABLE_UNIFIED_MEMORY.
- worker.py _rocm_classify_unified_memory: add gfx1152 to the arch set,
and 860m/840m to the device-name fallback. The NVIDIA GeForce 840M
cannot collide there: the function is only reached under _hw.IS_ROCM.
- llama_cpp.py _amd_apu_wants_unified_memory: add gfx1152 to the arch set.
- Tests for both, including the :sramecc-:xnack- suffix form.
TestGfx211AllowlistParity compared four hardcoded allowlist strings, so
adding gfx1152 to all four installers correctly turned three assertions
red without any installer actually disagreeing with another. Each test
now extracts the set its installer holds and compares it to one EXPECTED
constant. Order and spacing are free, membership is not, and the next
leaf is a one-line edit instead of four.
* [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
---------
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
Co-authored-by: Daniel Han <danielhanchen@gmail.com>
* Studio: reset quantized KV cache to f16 when flash-attn-off fallback fires
Studio force-enables --flash-attn on for GGUF launches. On a hard startup
or first-decode crash it retries via _with_flash_attn_off, which flipped FA
off but left --cache-type-k/-v untouched. A quantized KV cache (q8_0, q4_0,
q4_1, q5_0, q5_1, iq4_nl) requires flash attention in llama.cpp, so the retry
itself aborted at init with 'V cache quantization requires flash_attn' instead
of recovering.
Reset any quantized --cache-type-k/-v to f16 in the FA-off fallback path so
the retry can actually launch. Non-quantized types (f16, bf16, f32) run fine
without flash attention and are left unchanged. Handles long and short flag
forms and both space and equals syntax, rewriting in place to preserve list
length. Adds pytest coverage.
* [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
* Studio: FA-off fallback resets only the quantized V cache and drops env-only V cache
Only the V cache requires flash attention in llama.cpp; a quantized K cache
runs fine without it. Restrict the FA-off crash-recovery reset to the V axis
(main and draft) so a memory-constrained config keeps its quantized K cache
instead of risking an OOM on the recovery. Also drop an inherited quantized V
cache set purely through the environment (LLAMA_ARG_CACHE_TYPE_V /
LLAMA_ARG_SPEC_DRAFT_CACHE_TYPE_V) at the FA-off retry sites, which the argv
rewrite cannot reach, so the child falls back to the f16 default rather than
aborting.
* Studio: normalize underscore V-cache aliases in the FA-off fallback
llama.cpp rewrites '_' to '-' for any '--' long option before matching,
so a pass-through --cache_type_v q8_0 enables a quantized V cache just
like --cache-type-v. The FA-off crash-recovery reset only matched the
hyphenated spelling, so the underscore alias slipped through and the
retry still aborted with "V cache quantization requires flash_attn".
Canonicalize the flag name the same way before matching (short flags and
the type value are untouched).
* [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
---------
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
Resolve the drift between PR #6763 and current main:
- deletion: main moved cached-model deletion into hub/services/models/deletion.py,
so the PR's Images/Video in-use guards move there too as _diffusion_blocks_delete
and _video_blocks_delete, keeping main's fail-closed 503 contract.
- llama_keepwarm: take main's rewrite, re-apply the PR's image/video inference
suffixes so a generation in flight blocks an idle unload.
- routes/training: keep main's sidecar-swap 409 and resume_source_run_id, run
start_training in the worker thread the PR's unload hook needs.
- model picker: main renamed components/assistant-ui/model-selector ->
features/model-picker/... and rewrote pickers.tsx, so the PR's picker work is
ported onto main's version (task/catalog props, task gating of hub + cached +
local rows, single-device expanderGpuGb, fine-tuned section hidden when scoped)
rather than reverting main's pinned-models and per-model-config work.
- images/video pages: imports repointed at the new model-selector path.
- tests: delete-guard tests retargeted at the deletion service.
Typecheck, i18n parity and model-catalog checks pass.
* Fix reasoning-only Qwen3.6 completions in Studio
* Address reasoning-only review findings
* [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
---------
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
* fix(studio): stop false MTP/vision capability reports (#7302)
MTP probing only inspected the first physical --spec-type help line and
treated empty/crash --help output as "lacks MTP", which false-warned on
otherwise capable builds. Parse the full --spec-type help block, fail open
when the probe is inconclusive, and stop blaming bare mmproj crashes on a
projector-format mismatch when the text-only retry also fails.
Fixes#7302
* [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
* fix(studio): tighten MTP probe semantics per Codex review (#7302)
Treat nonempty --help without --spec-type as definitive no-MTP, keep only
empty/crash probes inconclusive, skip binary_no_mtp UI hint on inconclusive
loads, and stop reporting supports_mtp=True in /status for unknown probes.
* Treat failed llama-server --help probes as inconclusive (#7302)
Gate definitive no-MTP results on a zero exit code so crash diagnostics with
nonempty stderr do not re-enable the false lacks-MTP warning path.
* Add returncode to probe test mock so probe_ok gating passes
* [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
* Fail open in /status when the MTP probe is inconclusive
* [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
* Report missing llama-server as lacking MTP in /status
* [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
* Tighten comments in MTP/mmproj probe changes
---------
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
Co-authored-by: Daniel Han <danielhanchen@gmail.com>
---------
Co-authored-by: Daniel Han <danielhanchen@gmail.com>
Co-authored-by: Roland Tannous <115670425+rolandtannous@users.noreply.github.com>
Co-authored-by: oobabooga <112222186+oobabooga@users.noreply.github.com>
* fix(studio): resolve bare git on Windows sandbox PATH
Sandboxed terminal tools rebuilt PATH as venv + System32 only, so
user-installed Git under Program Files never resolved by bare name.
Append absolute host PATH dirs after the curated prefix and inherit
PATHEXT on Windows (#7317).
* [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
* fix(studio): restrict sandbox PATH inheritance to Windows Git dirs (#7323)
Only append Git-for-Windows install directories from the host PATH on
Windows, instead of every absolute entry. This fixes bare `git` resolution
(#7317) without letting user-writable dirs (venv, node_modules/.bin)
shadow auto-safe terminal commands.
* Pin sandbox PATHEXT to block cwd script hijacks (#7317)
Use a fixed .EXE;.COM list instead of inheriting the host PATHEXT so
cmd cannot resolve auto-approved bare names from workdir .BAT/.CMD stubs.
* Resolve sandbox git dir via shutil.which and disable cwd exe lookup
* [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
* Keep non-exe git launchers resolvable under restricted PATHEXT
* [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
* Restrict inherited sandbox git dir to system install roots
* [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
* Drop SystemRoot trust and canonicalize short paths for sandbox git
* [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
* Resolve Program Files via known-folder API and append canonical git dir
* [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
* Trust native Program Files on 32-bit Windows and stub program roots in tests
* [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
* Scan PATH for a trusted git and derive native Program Files root
* [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
* Drop ProgramFiles env from the trusted-root fallback
* Fail closed when trusted Program Files root cannot be resolved
---------
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
Co-authored-by: Daniel Han <danielhanchen@gmail.com>
* Studio STT: only load safetensors weights for custom dictation models
The STT sidecar accepts arbitrary Hugging Face owner/model repos for
custom dictation models and, when safetensors were absent, downloaded
and loaded pytorch_model.bin through WhisperForConditionalGeneration
.from_pretrained. PyTorch checkpoints are pickles that execute code
during deserialization, and this path does not run the malware gate the
normal model loader applies, so an authenticated client on an exposed
Studio instance could load a crafted Whisper-looking repo and run code
in the backend.
Restrict custom STT repos to safetensors: the snapshot selector no
longer falls back to pytorch_model.bin(.index.json), the cached-snapshot
completeness check ignores pickle weights, and the load forces
use_safetensors so a stray cached pickle still cannot execute. The five
curated Whisper defaults already ship safetensors only, so this changes
nothing for the built-in models.
* STT: reject safetensors indexes that reference non-safetensors shards
A safetensors index (model.safetensors.index.json) is attacker-supplied
JSON and can name pytorch_model-*.bin shards in its weight_map.
Transformers dispatches shard loading per file by extension, so those
.bin shards still load through torch.load (pickle) even with
use_safetensors set. Require every weight_map value to end in
.safetensors in both the snapshot selector and the completeness check so
no pickle shard is downloaded or reused.
* Studio: add Voice settings tab (dictation, dictionary, read aloud)
New Voice tab in Settings, placed just before About:
- Dictation: microphone picker, browser STT engine, recognition language,
and an inline mic test with a live transcript
- Dictation dictionary: entries rewrite matching speech to their exact
spelling and casing, applied in both dictation paths
- Recent dictations: last 20 final transcripts with copy and clear, so
text can be recovered if it lands in the wrong place
- Read aloud: optional button on assistant responses with two engines,
curated system voices (novelty and legacy voices filtered, quality
ranked, capped at 20) or the TTS audio model loaded in Unsloth via
/audio/generate (e.g. Orpheus), plus speed, pitch, volume and preview
Settings persist in localStorage (unsloth_voice_settings) and are read
at call time so changes apply without reloading the runtime. Adds en
keys plus the tab label for ja, zh-CN and pt-BR.
* Studio: drop the single option STT engine select, rename TTS option
The STT engine dropdown only had one entry, so it added noise without
giving a real choice. The engine row can come back once local STT
models land. Also renames the TTS engine option Unsloth TTS model to
Load TTS model to make the action clearer.
* Studio: harden Voice settings against edge cases found in simulation
Simulated the feature across Chromium, Firefox and WebKit plus node
level unit runs and backend contract checks. Fixes from the findings:
- Dictionary rewrite used a replacement string, so entries containing
dollar patterns corrupted transcripts (A$$AP became A$AP, $& injected
the match). Switched to the callback form of String.replace
- Persisted voice settings now validate types on hydration: non string
micDeviceId, dictationLanguage and ttsVoiceURI, and non boolean
ttsEnabled fall back to defaults instead of flowing into the UI
- Dictionary entries are trimmed, capped at 120 chars and re-sanitized
on hydration
- The Test dictation panel now falls back to the default microphone
when the saved device is unplugged, matching the composer adapter
Test coverage: 46 unit assertions (dictionary regex edge cases across
unicode, word boundaries and injection, voice curation for simulated
macOS, Windows and Linux voice inventories, corrupt storage merge),
13 backend contract checks against /audio/generate on an isolated
instance, and 60 browser assertions across the three engines covering
rendering, degradation without SpeechRecognition, curation in a real
DOM, dictionary persistence with unicode and dollar entries, the
no-model preview error path and corrupt localStorage recovery.
* Studio: address Voice settings review feedback
Verified each review comment before acting. Confirmed and fixed:
- Editing a dictionary entry was broken in two ways: the store trimmed
on every keystroke so spaces could not be typed, and clearing the
field deleted the entry and unmounted the input mid edit. Updates now
keep the raw value and a blur commit trims or removes the entry
- The unplugged mic fallback checked instanceof DOMException, but a
cross browser probe showed Firefox and WebKit throw
OverconstrainedError objects that are not DOMExceptions, so the
fallback never fired there. Matching on the error name now
- When the browser ended a dictation test on its own (silence timeout),
the mic stream stayed open. All recognition end paths now stop the
tracks and save the transcript through a single finalize path
- The studio TTS audio element now releases its WAV data URL as soon as
playback ends, fails or is cancelled
- Allow microphone now reports insecure contexts (no mediaDevices)
accurately instead of claiming access was blocked
- Voice tab copy moved into i18n keys per src/i18n/AGENTS.md, so locale
overlays can translate it; en is the baseline and parity passes
- unsloth_voice_settings added to the Reset all local preferences key
list so voice preferences obey the reset
- Non default microphones note that the system default is used when the
browser speech engine cannot bind a specific device, since browsers
without the start(track) overload ignore the argument silently
Re-ran the full simulation set after the changes: 46 unit assertions,
13 backend contract checks and 60 browser assertions across Chromium,
Firefox and WebKit all pass, plus a dedicated browser probe for the
dictionary editing behavior.
* Studio: use the chat mic icon in Voice settings for consistency
The Voice tab and its buttons used the hugeicons Mic02 glyph while the
chat composer uses a custom filled mic. Extract that composer icon into
a shared lib/mic-icon component, drop the duplicate inline copies in
thread.tsx and shared-composer.tsx, and use it for the Voice tab icon
and the tab's mic buttons so the microphone looks the same everywhere.
* Studio: address second round of Voice settings review feedback
Verified each new comment against the current code first. One item was
already fixed in the previous round (recording transcripts when the
browser ends a dictation test on its own). Confirmed and fixed:
- The microphone row showed a picker with generic names when browsers
enumerate unlabeled devices before permission, leaving no way to
grant access from the row. It now branches on whether labels are
visible and shows Allow microphone otherwise
- Compare chat dictation ignored the selected microphone. It now opens
the chosen device with the same fallback rules as the main adapter,
passes the track to recognition where supported and releases the
stream when recognition ends
- Closing the Voice tab cancelled the shared speechSynthesis even when
read aloud was playing a chat message. Cleanup now only cancels when
the tab owns an active preview
- Double clicking Start test could race two recognizers and leak the
first stream. A starting flag set before the getUserMedia await makes
start reentrancy safe
- Turning off the read aloud setting mid playback removed the only stop
control. The stop button now renders whenever a message is speaking
- When an engine lacks the start(track) overload, both dictation paths
now release the selected device stream before retrying with the
default microphone instead of holding it open
- Read aloud support no longer requires Web Speech synthesis: the
Unsloth TTS engine only needs audio playback, so it stays available
in WebViews without speechSynthesis, with a clear error if the system
engine is chosen there
Not addressed here: cancelling in flight backend TTS generation on
stop. The route runs generation in a worker thread without a
cancellation path, which is shared pre existing behavior with audio
chat generation and belongs in a backend change.
All suites re-run green: 46 unit, 13 backend contract and 60 browser
matrix assertions across Chromium, Firefox and WebKit, plus probes for
the unlabeled device branch and the double click race.
* Studio: drop empty and duplicate voiceURIs so the Voice tab never renders a crashing Select item
* Studio: guard dictation mic lifecycle in Voice test and Compare composer
Release a microphone opened after the component unmounts, and stop Compare
dictation on a permission or security failure instead of silently recording
from the default device, matching the main chat adapter.
* Studio: fix dictation and read-aloud lifecycle edge cases in Voice settings
- Join final dictation chunks with a space so recorded transcripts do not merge words
- Ignore a stale recognizer onend so a quick stop then restart is not torn down
- Use previewingRef so a double click on TTS preview does not orphan the first request
- Keep the read-aloud stop control visible when a new run starts while a message is spoken
- Stop the dictionary remove button from deleting an adjacent entry on a blur then click race
* Studio: trim redundant Voice settings comments
* Studio: fix Voice preview and Compare dictation edge cases
- Only cancel the shared speechSynthesis for a system-voice preview, so stopping
a Studio preview no longer stops an unrelated chat read-aloud
- Release the Studio preview audio and its WAV data URL on normal completion
- Iterate every finalized result in Compare dictation so batched phrases are kept
- Cap persisted recent dictations to the last 20 on hydration
* Studio: use clipboard fallback for recents and release failed preview audio
- Copy recent dictations via the copyToClipboard helper so the execCommand
fallback works in Safari and insecure http LAN contexts
- Release the Studio preview audio when play() rejects, not just on ended/error
* Studio: add local speech-to-text dictation engine
Add an offline dictation engine that transcribes with a local faster-whisper
model, alongside the existing browser (Web Speech) engine. The browser engine
streams audio to Apple or Google speech services and needs internet; the new
engine runs on the server, works offline, and drives any chat model without
evicting it (it loads in the backend process, separate from the model
subprocess). It also gives Firefox dictation, which has no Web Speech support.
Backend: a lazily-loaded, kept-warm faster-whisper sidecar and three routes
under /api/inference/audio (stt/status, stt/load, transcribe). faster-whisper
is torch-free, so this does not disturb the existing model stack.
Frontend: a Dictation engine setting (browser or local model), a curated model
picker with sizes, and MediaRecorder capture posted to the transcribe route.
The model warms automatically when the engine is selected, with live status.
* Studio: stream local STT transcription as you speak
Local dictation showed nothing until you stopped, because the whole clip was
transcribed once on stop. Now the growing recording is re-transcribed on a
fast pass every second and emitted as live interim text, with an accurate
final pass on stop. Partial recordings decode fine, and the model refines
earlier words as more audio arrives.
Adds an interim flag to the transcribe route (beam 1, no VAD) for the fast
preview pass; the final stop uses the accurate path.
* Studio: make local dictation stop instant and reliable
Stopping local dictation waited for a final network transcription before the
session ended, so the stop button did not flip and a second click ended the
session early and dropped the text. Now stop commits the live transcript
immediately, releases the mic at once, and ignores a second stop while
finalizing. Previews run more often so the committed text is current.
* Studio: record local dictation in short clips for reliable streaming
Re-transcribing a growing buffer every second got slower as it grew, flooded
the backend, showed stale words, and could leave the stop button stuck waiting
on a backlog. Record short independent clips instead and transcribe each once,
appending the text as you speak. Work per clip is bounded, so stopping is
prompt (with a hard timeout as a safety net) and long dictations stay smooth.
* Studio: dictate then transcribe once on stop, ChatGPT style
Local STT dictation streamed by re-transcribing the growing clip, which
was quadratic and saturated the backend (multi-second lag), and stop only
halted the recorder without releasing the mic, so it kept recording. Record
the microphone continuously, release it the instant the user stops, and
transcribe the whole clip once. Stopping is immediate and the transcript
lands in about a second. Also add the tiny model for the fastest option.
* Studio: surface dictation and read-aloud failures instead of failing silently
- Compare dictation reports microphone and speech-recognition errors via toast,
reusing the main chat adapter's describeMediaError and describeSpeechError
- Read-aloud toasts genuine model or synthesis failures while ignoring cancellations
* Studio: ChatGPT-style recording bar for dictation
Clicking the mic now drops the composer into a dedicated recording bar
with a live waveform, a discard (X) and a confirm (tick), instead of a
plain stop button. The tick stops recording and transcribes the clip;
the X throws the recording away and keeps whatever text was already in
the composer. The model adapter taps the mic with an analyser to drive
the waveform, and the router tracks the live session so the X can cancel
it without transcribing.
* Studio: transcribe dictation while speaking, ChatGPT layout
Match ChatGPT's recording layout: the bar now renders in place of the
input with the left plus button kept, the waveform in the middle, and
the discard and confirm buttons together on the right.
Cut the post-confirm delay by transcribing in the background as the user
talks. The audio is split at natural pauses (voice-activity detection off
the same analyser that drives the waveform) and each clip is transcribed
as it is cut, so confirming only has to finish the short final tail. The
model is also warmed when recording starts so the first run never pays a
cold load.
* Studio: ChatGPT waveform, hide tools while dictating, faster STT
Make the recording UI read like ChatGPT: the waveform is now a dense row
of round dots that rise into thin centered bars, and while dictating only
the plus button shows, with the mode badge and tool toggles hidden so the
bar is just the waveform and controls.
Speed up transcription: decode greedily (beam_size=1), which is several
times faster on CPU with negligible accuracy loss on short dictation
clips, and cap background segments at 6s so the final tail after confirm
stays short.
* Studio: finish ChatGPT voice bar and low-latency STT
* [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
* Studio: full-width waveform with a timer that freezes on stop
Use the full-width waveform for the recording bar: brighter, bigger bars
that advance on a fixed cadence (keeping peaks between advances) so they
glide instead of racing by, inset from the composer edges. Keep a visible
timer and the green confirm button, matching the ChatGPT reference, and
freeze the timer and waveform the moment the user confirms.
* Studio: fix multilingual local dictation
* Studio: speed up dictation and release local STT
* Studio: harden dictation finalization and STT decoding
* Studio: restore Firefox dictation fallback
* Studio: add dictation history manager
* Studio: manage speech model downloads
* Studio: remove em dash from voice model label
* Studio: move dictation history into Voice
* Studio: source local STT from Unsloth Whisper models
Point the dictation STT sidecar and its Model Hub download entries at
Unsloth's Hugging Face Whisper repos (small, large-v3-turbo, large-v3)
and run them through Transformers, so Studio only ever downloads
Unsloth-uploaded weights. Drop faster-whisper and the Systran/mobiuslabs
repos; keep the Model Hub as the only download path via local_files_only,
and keep PyAV for audio decoding.
Device selection uses float16 on CUDA and float32 on MPS and CPU, since
Whisper's decoder is unstable in float16 on MPS and repeats tokens.
Shorten the model picker labels to name plus download size and update the
STT tests for the new backend.
* [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
* Studio: smooth dictation waveform and keep pill height
* Studio: align STT model dropdown width and tidy voice copy
* Studio: guide to local engine when browser dictation is offline
* Studio: clarify voice section and STT model copy
* Studio: keep STT warm with training-aware eviction
* Harden STT lifecycle and browser compatibility
* [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
* Fix model discovery test lint
* Harden cross-browser microphone errors
* Harden cross-browser microphone errors
* Surface voice test recognition errors and fall back to Studio TTS
- Voice test now toasts non-abort speech-recognition failures instead of
ending silently, matching the main and Compare dictation paths.
- Read-aloud routes to the backend model when the runtime lacks Web Speech
synthesis (audio-only WebView), so it no longer errors immediately.
* Fix reviewed STT lifecycle races
* [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
* Fix read-aloud fallback controls
* Guard read-aloud stop when deleting a non-speaking message
aui.message().stopSpeaking() throws unless this message is the one being
read aloud, so calling it unconditionally rejected the delete handler before
the message was removed. Only stop speech when this message is speaking.
* Cap recent dictation transcript length before persisting
Recent dictations only limited entry count, so a long transcript stored the
full text in the persisted voice settings and a few could exceed the
localStorage quota, throwing synchronously from the uncaught dictation cleanup
path. Truncate each entry on save and on hydration, matching the dictionary cap.
* Studio: keep dictation mic clickable and guide to local model
Register the dictation adapter unconditionally so the mic stays enabled
for any engine and starts working right after switching to the local
model on an already-open thread.
When the browser engine cannot run (Firefox, Brave, non-secure origins),
clicking the mic shows a toast that points to the local speech-to-text
model instead of leaving a disabled button. The toast stacks its action
below the text with a fully rounded button.
* Studio: add bottom padding below the dictation guidance toast button
* Studio: increase bottom padding under the dictation toast button
* Studio: add bottom padding inside the dictation toast button
* Studio: add five Whisper defaults and custom model search
Add private UnslothAI Tiny and Base mirrors to the curated local STT choices while keeping Small as the default. Let users search or paste a Transformers-compatible Whisper repository and validate it end to end.
Keep short dictations in one clip to avoid repeated padded encoder work, then split longer recordings near Whisper's 30-second boundary.
Update hidden model filters and tests, including the CPU-only CI runtime stub for PyAV.
* [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
* Studio: use public Unsloth Whisper repositories
Point the Tiny and Base dictation defaults to the public unsloth repositories and remove the private mirror references from model filtering and tests.
* Studio: update Whisper download sizes
Reflect the cleaned public Tiny and Base repositories in the curated model labels.
* Studio: right-align STT model size, fix dropdown wheel scroll, refresh sizes
- Show the download size on the right of each model row so long names
like Whisper Large v3 Turbo no longer hide it
- Update curated Whisper sizes to the safetensors weights actually
downloaded: Tiny 151 MB, Base 290 MB, Small 967 MB
- Drive the model list scroll from a wheel handler so the mouse wheel
scrolls it inside the Settings dialog, not just the scrollbar
- Add a search icon and shorten the placeholder to Search model
* Studio: do not search when a dictation model is picked, shrink repo label
- Treat the filled-in model text as a selection, not a query, so choosing
a model no longer kicks off a Hugging Face search
- Make the repository line under each model name smaller
* Studio: tighten dictation model and local engine descriptions
* Studio: keep model display on pick instead of the query, shrink row text
- Guard the combobox input so selecting a model shows its name and does
not echo the typed query back or start a search
- Map the item label to the friendly display so picks fill the field
- Reduce the model name and size text in each row
* Studio: show only the model name in the dictation field, shrink size label
- Drop the download size from the search field; the name alone is shown
once a model is selected, with sizes kept in the dropdown list
- Reduce the size label text in each row
* Studio: clarify the dictation model description
* Studio: drop Hugging Face from the dictation model description
* Studio: move the dictation dictionary to its own Manage subpage
- Replace the inline entry list with a Manage row, matching Dictation
history, so a long dictionary no longer crowds Voice settings
- Add a DictationDictionaryView subpage that holds the entry editor
* Studio: match STT field font, use best voice for System default
- Bump the dictation model field text to text-sm so it matches the
engine dropdown next to it
- Resolve the System default read-aloud voice to the top curated voice
instead of the browser default, which is a robotic legacy voice on macOS
* Studio: rerank read-aloud voices and drop duplicate voice entries
- Rank by vendor quality, then the user's locale, then a preferred list of
natural voices, so the best voice leads instead of the first alphabetically
- Collapse voices that macOS reports twice under one name and language
* Studio: fold dictionary and recents into the dictation section
- Drop the separate Dictation dictionary and Recent dictations headings;
their Manage rows now sit under Dictation, split by the row divider
- Shorten the custom spellings description
* Studio: add search and sort to dictation history
- Filter saved dictations by text with a search field
- Sort by newest, oldest, or A to Z; show a no-matches message
- Keep Clear all available regardless of the current filter
* Studio: settle cancelled STT loads before training and fix dictation review items
Wait for a cancelled STT load to exit and release its memory before
reporting it freed for training, so the loader cannot still be inside
from_pretrained()/.to(device) holding VRAM when the training subprocess
starts. A load that finishes before observing the cancel now gets
unloaded so the memory is actually reclaimed.
Clear the accelerator cache before the CPU fallback in load() so a failed
CUDA/MPS load does not strand reserved VRAM once the sidecar is marked
CPU-resident.
Send the saved Hugging Face token when polling STT download progress so a
gated or private repo resolves and shows the correct Load/Downloaded
state instead of reporting missing.
Mark the composer Dictate button as type="button" so clicking it does not
also submit the draft when the composer already has text or attachments.
* Studio: pin dictation settings per session and close STT startup races
Capture the STT model and language when a dictation session starts and
pass them to every queued segment and the warm-up load, so changing the
model or language mid-recording no longer transcribes the same clip with
the wrong model or a model that is not downloaded.
Check the local runtime at the top of transcribe(), before the model
cache lookup and the bounded audio decode, so a server missing PyTorch or
Transformers returns 501 up front instead of decoding a long clip first.
Treat the training startup window as active for STT device selection.
start_training frees VRAM in before_spawn but only assigns _proc later, so
a concurrent STT load could take the GPU that was just cleared. A startup
flag now reports training active from the free until the process is live,
forcing those loads to CPU; a finally clears it on every exit.
* [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
* Studio: stub the STT runtime check in transcribe orchestration tests
transcribe() now verifies the local runtime up front, so the unit tests
that exercise transcription orchestration must treat the runtime as
present to keep passing where PyTorch, Transformers, and PyAV are not
installed. Stub ensure_stt_available in the shared fixture and restore
the real check in the availability and load-rejection tests.
* Harden custom Whisper dictation models
* [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
* Add whisper.cpp dictation engine with per-engine downloads and history rework
Engines
- New GGML STT sidecar that runs a managed whisper-server subprocess with
idle unload, plus a pinned static build script (scripts/build_whisper_cpp.sh)
- Dictation engine picker now offers Browser, Local transcription
(whisper.cpp), and Local transcription (Transformers)
- Both local engines serve the same five curated Whisper models and download
them directly with byte-level progress reported by /audio/stt/status
- Models auto load on selection and when their download finishes
- Unload and training admission account for both engines
Benchmarks (Apple Silicon, greedy, warm, same checkpoints)
- whisper.cpp transcribes 2.4x to 5x faster than Transformers and loads in
about 0.45s vs 0.86s for Whisper Small
- whisper.cpp GGUF path is unchanged by the Transformers addition
(load 0.445s -> 0.444s, short clip 0.391s -> 0.347s, long 1.197s -> 1.129s)
Voice settings UI
- Plain curated model select replaces the searchable combobox
- Single download progress bar with transfer rate for both engines
- Dictation history now stores every dictation with Show more pagination,
a top Clear history action, and links back to the chat it was spoken into
- Archived chats dialog gets the same pagination
- Delete dialog offers deleting a dictation together with its chat
Tests: 88 backend STT tests pass, including new snapshot download coverage.
Frontend typecheck, lint, i18n parity, and production build pass.
* Merge local engines into one option and source GGML models from unslothai
Engine selection
- The dictation engine dropdown is back to two choices: Browser and Local
transcription. The selected model decides the backend: curated ids run
GGML checkpoints through whisper.cpp, searched Hugging Face repositories
run safetensors through Transformers
- Model picker lists the curated models and searches Hugging Face for other
Whisper repositories, validating them before selection. The trigger is a
plain button so the selection never renders inside a text input
- /audio/stt/status accepts a model query param so downloaded state works
for custom repositories; the engine param on load, transcribe, and
download routes is derived from the model everywhere
Model source
- Curated GGML checkpoints now download from the Unsloth-hosted
unslothai/whisper-*-GGUF repositories (one repo per model) instead of
ggerganov/whisper.cpp; cache lookups, progress totals, and in-flight blob
tracking are per-model
Fixes
- Voice settings and dictation history were not persisting: the quota-safe
localStorage wrapper was declared after the store that uses it, so the
persist storage factory failed silently. Every settings write also threw
mid-click, which kept the model picker popover from closing on selection
- is_model_downloaded now verifies config, preprocessor config, and real
weight files instead of trusting an offline snapshot lookup, so a partial
download left by an aborted fetch shows the Download button instead of
failing to load
- Removed whisper.cpp mentions from user-facing text: the ready status
shows Loaded instead of the runtime name, picker rows show the source
repository, and runtime error messages say local transcription runtime
Verified with automated browser sessions and live API checks: selection
closes the picker with no page errors, persisted settings hydrate on
reload, a stale partial snapshot triggers download then loads on MPS and
transcribes, and curated models download from the unslothai repos. 88
backend STT tests, typecheck, lint, i18n parity, and build pass.
* Skip the duplicate source line for custom models in the STT picker
A custom repository's display name is its id, so search results and the
appended current selection rendered the same string twice. The source
line now only renders when it differs from the name; curated rows keep
their name, unslothai source repository, and download size.
* Verify every shard of a sharded checkpoint in the downloaded check
A snapshot holding one of N shards (or a corrupt shard index) passed the
downloaded check and then failed at load. When model.safetensors.index.json
exists, every shard in its weight map must now be present. Found by
simulation; covered by a regression test.
* [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
* Rename stale _starting references in the pump resilience tests
The startup flag on TrainingBackend was renamed to _spawn_in_progress but
two tests added alongside it still asserted on the old name, failing the
Python 3.11 to 3.13 CI jobs.
* Make the selected model row clearly highlighted in the STT picker
The current selection was a faint background tint. It now uses the accent
background with a medium weight name. Two line rows use a small corner
radius; single line custom repo rows keep the pill shape.
* Address review feedback on STT snapshot checks, VRAM release, and dictation UX
Verify snapshot completeness in the load preflight so a partial download
fails before the audio is decoded, for curated and custom repos alike.
Drop the failed accelerator traceback before the CPU retry so the cache
clear can actually release that memory. Keep unloading the GGUF sidecar
after cancelling an in-flight Transformers load; both engines can hold
memory at once. Allow Auto language with English-only .en checkpoints,
matching the backend which sends no forced language. Keep the discard
button usable while a transcription is pending so a slow or hung request
cannot trap the composer in dictation mode. Stop linking Compare and
settings test dictations to the unrelated active single chat thread.
* [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
* Move the CPU retry out of the exception handler
On Python 3.10 the interpreter exception state keeps its own reference
to the traceback, so dropping it from the caught exception was not
enough to release the failed accelerator load during the retry. Leaving
the handler before clearing the cache works on every supported version.
* Address review feedback on session handoff, chat pinning, and server lifetime
Starting a dictation from a second entry point now cancels the session
it replaces, so the old recording cannot keep the microphone open or
save a transcript with no discard button pointing at it. The linked
chat is pinned when recording starts, so switching threads while a
transcription finalizes cannot relink the transcript to the newly
opened chat. whisper-server is now bound to Studio's lifetime like the
other long-lived children: PDEATHSIG on Linux, the parent job object on
Windows, and pid adoption so the shutdown sweep reaps it; before this
it survived a Ctrl+C exit as an orphan still holding the model.
* Remove the dictation mic test from Voice settings
The composer dictate button covers the same check, so the test row, its
transcript panel, the unsupported fallback row, and their strings and
search entry are gone.
* Studio STT: gate GGUF whisper-server on training and fix dictation retry and dictionary edits
GGUF (whisper.cpp) sidecar:
- Launch whisper-server with --no-gpu while training is active, mirroring the Transformers sidecar's CPU device choice, so a mid-training dictation cannot reclaim the VRAM training just freed.
- Report is_loading() during whisper-server startup so training VRAM admission accounts for the accelerator memory it is about to bind.
- Require PyAV in is_available() so /audio/stt/status reports the engine unavailable when uploads cannot be decoded, instead of loading fine and then 501ing at transcription.
- Reject a missing model before decoding audio, matching the Transformers download preflight.
Voice settings:
- The download Retry button now restarts the download; the sidecar error is sticky until a new start(), so re-polling alone never cleared it.
Dictation dictionary:
- Tabbing from an emptied entry to its remove button no longer commit-splices the row first, which shifted indices and deleted the wrong entry.
* [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
* Studio STT: fix curated GGUF whisper filenames to match hosted repos
The unslothai/whisper-*-GGUF repos host the checkpoint as whisper-<id>.bin,
not ggml-<id>.bin, so every curated dictation download and cached-path
lookup 404'd and the whisper.cpp engine could never load a model. Point
GGML_STT_MODELS at the real filenames and guard the naming with a test.
* Studio STT: validate a custom dictation repo before downloading it
The Transformers STT engine accepts an arbitrary owner/model repo, but the
download route handed it straight to snapshot_download, pulling a possibly large
non-Whisper repository into the shared HF cache. Confirm the repo is a Whisper
checkpoint first with the existing metadata-only validate_remote_model (no
weights); curated ids short-circuit and the GGUF engine (curated-only) is
unaffected. A non-Whisper repo now 422s before any download.
* Studio STT: preempt a still-loading GGUF server for training admission
A whisper-server still in its startup window binds accelerator memory but has no
loaded_model yet, so training admission could miss it and launch into an OOM.
Make the GGUF startup cancellable (cancel_pending_load signals an abort event and
terminates the starting process without the load lock; _wait_for_server observes
it and raises SttLoadCancelledError; wait_for_load_to_settle blocks on the lock
until the killed server is reaped), and always fold the GGUF sidecar into the
resident-STT summary so a resident Transformers model cannot mask a loading GGUF
server. free_stt_model_for_training now cancels an in-flight load and waits for it
to settle before training claims the memory.
* [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
* Studio STT: fall back to Transformers when whisper-server is absent
A curated dictation model (including the default small) hard-pinned the GGUF
engine, but standard installs do not ship whisper-server, so every recording
501'd instead of using the Transformers engine that serves the same checkpoint
-- the GGUF sidecar's own documented contract. Add _resolve_serving_stt_engine:
a GGUF request for a curated id (the only ids GGUF accepts, all Transformers-
servable) downgrades to Transformers when whisper-server is unavailable, applied
consistently to download, load and transcribe (not unload, which targets a
specific engine). The Voice tab likewise falls back to the Transformers status so
the model is not shown unavailable and download is not blocked.
* Studio STT: hide custom Whisper caches from the legacy model pickers
The legacy /cached-models (and /cached-gguf) routes called is_hidden_model with
only the owner/model id, which cannot reach the config-based Whisper check, so a
downloaded custom (non-curated) Whisper checkpoint was still offered as a chat
model. Pass the cached snapshot path so _path_is_whisper_model inspects the repo
config and hides it, matching the discovery route.
* Studio STT: hide GGUF dictation repos, lock-free status, unload fallback, split training eviction
- Hide the curated GGUF dictation repos (unslothai/whisper-*-GGUF) from the chat
model inventory and pickers, backend and frontend. Only their Transformers
safetensors companions were hidden; the GGUF repos use a different org and a
-GGUF suffix and carry a raw .bin with no whisper config.json, so they leaked
into chat pickers.
- Make the GGUF sidecar loaded_model/device accessors lock-free, mirroring the
Transformers sidecar. transcribe() holds self._lock across the whole inference
call, so /audio/stt status polls and training admission previously blocked
behind an in-flight transcription.
- stt_unload resolves through the serving resolver: a "gguf" pick on a host
without whisper-server is served by the Transformers fallback, so unload must
target that engine or the resident model is never freed. Unload also attempts
every engine even if one raises, so a failure freeing one backend no longer
skips the other.
- free_stt_model_for_training frees the Transformers and GGUF sidecars under
independent exception boundaries so a failure unloading one no longer skips
the other before training claims the memory.
Adds tests/test_stt_review_fixes.py covering all four.
* Studio STT: resolve Auto dictation language for the model engine + snapshot process liveness
- The model dictation adapter sent the raw setting (the literal "auto") to the
backend, while the browser engine resolves Auto via resolveDictationLanguage.
A batch of non-English voice notes came back mostly English on Auto. Add
resolveModelDictationLanguage: only the literal "auto" is resolved to a
concrete locale, gated so it becomes a language the model AND Whisper can
honor (mirroring the backend's known-whisper-languages set); an explicit
language, or a locale Whisper cannot honor, stays unchanged/auto-detect. Wire
it into both adapter call sites.
- GgmlSttSidecar._process_alive() read self._process twice; a concurrent
unload() nulls it under the lock while loaded_model/device read lock-free, so
a null between the two reads called None.poll(). Snapshot once. Adds a
deterministic regression test.
* studio: tighten comments and docstrings in the dictation modules
* studio: harden dictation model downloads, GGML readiness, and recording paths
Address review findings on the STT dictation feature:
- build_whisper_cpp.sh refuses to delete a whisper.cpp tree under a custom
Studio home unless it carries the Studio ownership marker, matching the
setup.sh policy, and marks trees it creates
- _snapshot_is_complete validates every shard of a sharded PyTorch
(pytorch_model.bin.index.json) checkpoint like the safetensors path, and
requires tokenizer assets (tokenizer.json or vocab.json + merges.txt)
- custom-repo downloads pin the revision resolved at validation time and
restrict snapshot_download to the model/tokenizer/config/preprocessor file
classes Studio loads
- the GGML sidecar holds its port reservation until just before spawning
whisper-server and only accepts readiness from a responder that both looks
like whisper.cpp's server and belongs to the still-running managed child,
probing twice, so mic audio cannot be posted to a foreign local process
- the recording adapter transcribes every non-empty segment; the RMS meter
only shapes segment boundaries and can no longer discard quiet speech
- Compare-pane dictation can cancel a pending transcription on second click,
with the button relabeled while finalizing
- localStorage quota recovery halves the dictation history until the save
fits, so small histories shrink too
- the System default TTS voice resolves to the platform default voice
- new dictation UI imports go through the chat and hub feature barrels
Regression tests cover the build-script gate, sharded PyTorch and tokenizer
completeness, revision pinning and allow patterns, and the whisper-server
readiness probe.
* Fix STT download and voice picker follow-ups
* [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
* Add dictation button regression coverage
* Studio: prebuilt whisper.cpp via the shared llama.cpp install core, slim bundles paired to the llama prebuilt (#7294)
* Studio STT: add prebuilt whisper.cpp (whisper-server) installer
New install_whisper_prebuilt.py downloads a per-platform whisper-server
bundle published by the unslothai/whisper.cpp prebuilt CI into the managed
whisper.cpp dir (build/bin/whisper-server) so local dictation needs no
compiler. Mirrors install_node_prebuilt.py / install_llama_prebuilt.py:
host + backend detection, sha256 pins (whisper_prebuilt_pins.json) as the
trust anchor, staging + install lock + atomic swap, traversal-safe extract,
co-located shared libs (RUNPATH=$ORIGIN), an UNSLOTH_WHISPER_PREBUILT_INFO.json
marker with idempotent "already matches", and exit codes 0/1/2/3. Not wired
into setup yet; the pins ship empty so every asset fails closed until the
first fork release is published and its digests are reviewed in.
* Studio STT: install prebuilt whisper.cpp during setup and update
Add a fail-open whisper.cpp block to setup.sh after the llama.cpp section so
`unsloth studio update` (and a fresh install) fetch the prebuilt whisper-server
into the managed whisper.cpp dir the sidecar discovers. It skips a user-set
WHISPER_SERVER_PATH/UNSLOTH_WHISPER_CPP_PATH, honors UNSLOTH_SKIP_WHISPER_INSTALL,
forwards the resolved ROCm gfx, and never aborts setup: a busy install keeps the
existing runtime, and an unavailable prebuilt stays quiet (source build is opt-in
via UNSLOTH_WHISPER_FORCE_COMPILE) since Transformers STT and browser dictation
remain. Register UNSLOTH_WHISPER_PREBUILT_INFO.json as Studio-owned evidence.
* Studio STT: harden whisper-server child env + WSL ROCm detection
- Sidecar spawns whisper-server with a scrubbed child env that prepends the
binary dir (co-located GPU libs) to the loader path, and on WSL2 ROCm loads
the system HIP first (HSA_ENABLE_DXG_DETECTION=1) so a bundle's bare-metal HIP
does not segfault on /dev/dxg. Secret-bearing vars are dropped from the child.
- find_whisper_server_binary now requires an executable, not just a file.
- Installer rocm probe passes HSA_ENABLE_DXG_DETECTION and falls back to
/opt/rocm/bin/rocminfo so a WSL ROCm host is not misdetected as CPU-only;
gfx parsing skips the gfx000 CPU agent and generic ISA lines.
- Tests for the child env (secret scrub, lib dir, WSL HIP precedence), the
executable check, and the WSL rocm detection.
* Studio STT: in-app whisper.cpp prebuilt update stack + ship pins in the wheel
Mirror the llama.cpp update stack for the whisper.cpp prebuilt so Studio can
detect and install a newer whisper-server release from inside the app:
- backend/utils/whisper_cpp_freshness.py: read UNSLOTH_WHISPER_PREBUILT_INFO.json
and compare the installed release against the newest unslothai/whisper.cpp
release. Whisper tags are v<upstream>-unsloth.<N>, so is_behind compares a
(major, minor, patch, serial) key with a strict downgrade guard; 24h cache;
fail-open.
- backend/utils/whisper_cpp_update.py: run install_whisper_prebuilt.py to fetch
and atomically swap the newest bundle, unloading the warm GGUF sidecar first.
- backend/routes/whisper.py mounted at /api/whisper (update-status + update).
- pyproject: add whisper_prebuilt_pins.json to studio package-data so the
installer's trust anchor ships in the wheel (it is a data file, not a .py
module, so package discovery alone does not include it; node_prebuilt_pins.json
is listed for the same reason). Without this a pip-installed wheel had no pins
and the prebuilt install aborted to Transformers STT.
Adds test_whisper_cpp_freshness.py (version parser, is_behind matrix + downgrade
guard, marker layouts, stale decision, fail-open).
* Studio STT: verify whisper prebuilts via the release checksum index, like llama.cpp
Re-align the whisper.cpp prebuilt installer to install_llama_prebuilt.py's trust
model: instead of a committed whisper_prebuilt_pins.json, verify every download
against the release's own whisper-prebuilt-sha256.json checksum index, fetched
from the same GitHub release.
- parse_release_checksums / fetch_release_checksums / expected_sha256_for replace
the pins layer. The index is validated for schema/component and that its
release_tag matches the resolved release; an asset absent from it, a release
that does not publish it, or a manifest sha256 that disagrees with it all fail
closed to a source build.
- resolve_release_tag now resolves the newest published release at runtime (or an
explicit --published-release-tag), matching llama and the freshness check;
removed the pinned-default and the UNSLOTH_WHISPER_ALLOW_UNVERIFIED opt-in.
- Delete studio/whisper_prebuilt_pins.json and drop its pyproject package-data
entry (nothing to ship now, same as llama which has no committed pins).
- Adds test_install_whisper_prebuilt_checksums.py (index parser, fail-closed on
uncovered asset, tampered-manifest guard, newest-release resolution).
This is a same-origin checksum (integrity, not authenticity), identical to the
llama.cpp installer; pair releases with GitHub artifact attestations for provenance.
* Resolve whisper prebuilt release via the download host (no GitHub API)
Mirror install_llama_prebuilt.py's fast path: resolve the release tag from
the releases/latest redirect and fetch the manifest + checksum index from
constructed releases/download URLs, so the common install path makes zero
api.github.com calls (unauthenticated api.github.com is capped at 60 req/hour
per IP; the download host is not). Fall back to the GitHub API only on a 404,
malformed asset, or tag mismatch.
* Studio STT: coverage-aware whisper prebuilt selection via a shared core
whisper's select_artifact returned the first os/arch/backend manifest match and
ignored the SM-coverage fields the release manifest already carries, so a
Blackwell B200 (sm_100) was served cuda12-legacy (sms 50-61) -- runnable only via
forward PTX JIT. install_llama_prebuilt.py on the same host correctly picks
cuda13-newer.
Extract the coverage-aware selection into a shared, component-agnostic core under
studio/backend/utils/prebuilt/ (selection + GPU host-capability detection), lifted
from llama's linux_cuda_choice_from_release / _artifact_covers_sms / _sm_range and
generalised over a normalised artifact. whisper's HostInfo now records the GPU
compute caps + driver CUDA version (honoring CUDA_VISIBLE_DEVICES), and
select_artifact routes CUDA/ROCm through the shared selector: every visible SM
must be covered, the tightest-covering profile wins (Blackwell-aware runtime-line
ordering), ROCm matches the gfx target exactly, and an uncovered GPU falls back to
the CPU bundle. CPU/Metal/Vulkan keep first-match. The resolver JSON, exit codes,
and "already matches" contract are unchanged.
On the B200 the installer now resolves cuda13-newer, matching llama.
* Studio STT: gate whisper CUDA selection on the on-disk runtime, like llama
The prebuilt CUDA bundles are dynamically linked and intentionally do NOT ship
libcudart/libcublas -- they load the same runtime the host already has. So the
driver's advertised CUDA version is only an upper bound: a cuda13 bundle still
needs cuda13 runtime libraries present on disk. Port llama's on-disk runtime
scan (detected_linux_runtime_lines / detected_windows_runtime_lines) into the
shared core and intersect it with the driver-compatible lines in
select_cuda_attempts. A host with a cuda13 driver but only cuda12 runtime (e.g.
torch-cuda12) now correctly gets a cuda12 bundle instead of an unloadable cuda13
one; a host with no CUDA runtime at all falls back to CPU.
Fixes a glob bug in the port (any(Path(d).glob(p) for d in dirs) tests generator
truthiness, not a match) that made every major report present; add a real
filesystem test that exercises the scan.
* studio: harden shared prebuilt core to full llama parity
Apply the review findings on the shared coverage-aware prebuilt-consumer
core so whisper.cpp selection is exactly equivalent to the llama.cpp path.
hosts.py: port llama's CUDA_VISIBLE_DEVICES handling. A GPU hidden by an
index/UUID selector now reports has_usable_nvidia False instead of staying
usable, via supports_explicit_visible_device_matching plus the physical /
explicit-match branches, and _select_visible_rows now matches rows the way
llama does (index or UUID, gpu- prefix optional) and skips unmatched tokens
rather than keeping all rows. Adds the Linux /proc/driver/nvidia/gpus
fallback and has_physical_nvidia. Adds parse_macos_version.
runtime_libs.py: the Linux on-disk scan now requires the exact libcudart /
libcublas SONAME (libcudart.so.13), not a libcudart.so.13* glob, so a bare
versioned file without the SONAME symlink no longer counts as loadable.
Hardens the ldconfig parse against an empty left-hand side.
selection.py: fix the Blackwell/torch reordering so it keys on the covering
runtime lines (falls through to the torch preference when the covering lines
were filtered out), matching linux_cuda_choice_from_release. Corrects the
compatible_runtime_lines_for_driver docstring: the bundles do not ship the
CUDA runtime, so the driver version is only an upper bound and the caller
must intersect with the on-disk scan.
install_whisper_prebuilt.py: enforce a macOS artifact's min_os (new
HostInfo.macos_version) so a bundle that cannot load on the host OS version
is dropped. Keep resolver stdout to only the JSON line by leaving logs on
stderr in --resolve-prebuilt mode, and map an unexpected probe failure to
prebuilt_available False instead of a traceback.
Tests: new host-probe suite for the visible-device logic, exact-SONAME
runtime-scan cases, macOS min_os filtering, resolver stdout-only-JSON,
exit-code mapping, and the repo key.
* studio: fix whisper prebuilt selection + launch parity gaps from review
A parallel review surfaced integration defects where the whisper path could
select or launch a bundle that cannot run on a concrete host. Each is fixed to
match install_llama_prebuilt.py.
macOS min_os: the manifest labels macOS requirements as macos-<version>
(e.g. macos-14.0), which the version parser could not read, so the guard was a
no-op and a macOS-13 host would install the macos-14 Metal bundle. Strip the
platform prefix before parsing.
ROCm gfx detection: _detect_rocm_gfx returned the first gfx token and ignored
HIP_VISIBLE_DEVICES / ROCR_VISIBLE_DEVICES / CUDA_VISIBLE_DEVICES. Since exact
ROCm matching treats that token as the active GPU, a mixed APU + dGPU host
(gfx1151 + gfx1100) with HIP_VISIBLE_DEVICES=1 installed the wrong archive. Route
through a shared pick_rocm_gfx_target (lifted from llama) that parses per-GPU
sections and honors the visibility vars (empty / -1 -> no AMD GPU).
--rocm-gfx override: recording the arch without setting has_rocm left the host on
its CUDA/CPU path so the ROCm bundle was never picked. --rocm-gfx now implies
has_rocm and clears NVIDIA state, like llama's _apply_host_overrides.
CUDA launch env: a CUDA bundle ships the ggml CUDA backend but not
libcudart/libcublas, and the sidecar launch env exposed only the bundle dir, so
on a host whose CUDA runtime lives only in the PyTorch wheels the selection would
gate cuda usable but the server could not load it. Add the CUDA-from-PyTorch
runtime dirs to the child loader path for CUDA bundles (bundle dir still first),
mirroring binary_env.
Also normalize a manifest artifact's supported_sms defensively (parity with
llama's parser) and document that blackwell_min_toolkit_for_caps is retained for
the Phase B llama Windows path.
Not changed (verified parity, not defects): Linux/Windows min_os is enforced
nowhere in llama (macOS only); the resolver is optimistic about the checksum
index and the install path verifies.
* studio: tighten prebuilt-core code comments
* studio: lift shared prebuilt installer core out of the whisper installer
* studio: reuse the llama.cpp prebuilt installer machinery for whisper
* studio: unify llama and whisper prebuilt installers on a shared descriptor core
* studio: consolidate prebuilt installer tests into the shared core suite
Grow tests/studio/install/test_prebuilt_core.py from 62 to 164 tests so every
component-agnostic behavior runs against both descriptors: the full seven
profile CUDA release matrix (multi-GPU, on-disk runtime gating, shuffle
stability, missing SM metadata, dotted SM normalization, no-driver fallback
policy), the ROCm gfx family matrix, macOS min_os gating and its helper,
backend resolution incl. cpu-fallback precedence and Intel-mac auto detect,
checksum-index non-object and plain-lookup cases, the tar symlink/hardlink
extraction guards moved from the llama suite, and the compute-cap, visible
device, runtime-line and Blackwell helper value tables moved verbatim from
the llama characterization suites.
Delete only tests whose exact behavior the master now asserts for the same
component: 40 pure-alias helper cases in test_selection_logic.py (replaced by
value-identical master tables plus an alias-identity pin), 6 extraction moves
and the master-absorbed zip-symlink case in the llama logic suite, 3 routing
twins in test_rocm_support.py already pinned byte-for-byte in
test_selection_logic.py, the 2 Blackwell helper tables in the backend resolve
suite, 28 whisper logic tests and 10 whisper checksum tests re-asserted by
the master whisper parameterization. Wrapper wiring pins, the llama release
plan dialect, fingerprints and every llama-only behavior stay untouched.
* studio: dedupe sidecar and update helpers into the backend prebuilt package
* studio: chain whisper.cpp prebuilt updates onto the llama.cpp update flow
* studio: consume paired slim whisper prebuilts via the llama ggml runtime
* studio: serve every whisper backend from slim prebuilts
* studio: drop the whisper fat per-accelerator selection chain
unslothai/whisper.cpp releases are slim-only from v1.9.1-unsloth.2: one
ggml-less bundle per os/arch, paired to the llama.cpp prebuilt that provides
every ggml backend. Delete the whisper-side fat CUDA/ROCm/metal/vulkan
selection glue; keep slim selection + pairing, link_ggml_runtime, and one
legacy shape, the published fat CPU bundle of an explicitly pinned pre-slim
release. Exit 2 now reads as prebuilt unavailable (whisper never source
builds); setup already treats it that way.
* [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
* Wire libomp runtime DLL alongside ggml in slim whisper installs
llama's clang-built windows-arm64 ggml-base.dll imports
libomp140.aarch64.dll, shipped in the llama bundle but not a system DLL.
Without it next to whisper-server.exe the loader fails with
STATUS_DLL_NOT_FOUND before main. MSVC x64 links vcomp140.dll from
System32 and Linux ggml uses system libgomp.so.1, so only windows-arm64
was affected. The empty-runtime guard still requires a real ggml
library; libomp alone is not a pairing.
* studio: drop whisper-side fat-selection support structure
Slim whisper bundles are selected per os/arch only; all accelerator
capability comes from the installed llama.cpp prebuilt, whose installer
already did the coverage-aware selection. Remove the machinery that only
existed to pick among fat per-accelerator whisper bundles:
- prebuilt_core: delete the generic CUDA/ROCm coverage selection
(select_cuda_artifact, select_rocm_artifact, ArtifactView adapters,
detected_cuda_runtime_lines, the exact-SONAME linux probe) that no
shipped component routes through; llama keeps its own selection chain
and whisper shadows select_artifact with the slim-only version.
select_artifact is now a plain os/arch/backend first-match.
- install_whisper_prebuilt: drop the HostInfo CUDA fields
(compute_caps, driver_cuda_version, torch_runtime_line) and the torch
runtime probe that populated them; nothing reachable reads them, and
the resolver payload sources runtime_line from the artifact.
- whisper_cpp_update: delete the standalone start_update job worker;
whisper applies only run as the chained phase of the combined
llama+whisper update. The status payload keeps its job field (idle).
- routes/whisper: drop the progress logger that could never fire.
- tests: remove tests of the deleted paths and tests duplicating the
descriptor-parameterized core suite or the llama freshness suite.
Contracts unchanged: resolver JSON keys, exit codes, marker fields,
pairing logs, and the pinned pre-slim fat CPU escape hatch.
* Address review feedback on the whisper prebuilt update and install paths
- Pin the chained whisper phase to the release the freshness check
offered, so the download-host latest pointer cannot reinstall an
older build in a loop
- Wire the whisper prebuilt install into setup.ps1 (Windows setup
previously skipped it entirely)
- Treat a non-executable server or missing wired ggml libraries as a
broken install instead of reporting already matches
- Keep whisper sidecar reloads out of the job-level reload flag and
resync chat state after a partial chained update that unloaded llama
- Repoint home and profile vars for the whisper-server subprocess at a
managed scratch dir and drop credential-store pointers
- Clear the prebuilt marker before the opt-in source build overwrite
- Write the prebuilt marker with explicit utf-8 encoding
* Tighten comments in the whisper prebuilt consumer
* Harden the Windows whisper setup phase and the chained update edges
- setup.ps1: honor WHISPER_SERVER_PATH / UNSLOTH_WHISPER_CPP_PATH /
UNSLOTH_SKIP_WHISPER_INSTALL, run the custom-home ownership guard
before the atomic install, and forward the release-tag pin and ROCm
hints like setup.sh
- sidecar: a cpu-selected install launches whisper-server with --no-gpu
(slim wiring links every llama backend, so the flag is what keeps a
deliberate CPU choice off the GPU)
- chained update: leave whisper unpinned on macOS (the llama phase can
walk back there, and a newest-tag pin could be an impossible pairing
on every retry) and treat installer exit 2 as kept-existing-runtime
instead of failing the combined job
- job.to_tag now comes only from the llama phase, so a whisper-only
round cannot report a llama update that never ran
* Fix slim whisper runtime follow-ups
* Address remaining whisper update reviews
* [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
* Address remaining prebuilt update reviews
* Fix remaining chained update reviews
* Fix remaining whisper runtime review edges
* [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
---------
Co-authored-by: danielhanchen <unslothai@gmail.com>
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
Co-authored-by: oobabooga <112222186+oobabooga@users.noreply.github.com>
---------
Co-authored-by: danielhanchen <danielhanchen@gmail.com>
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
Co-authored-by: Unsloth <michaelhan@Michaels-MacBook-Pro.local>
Co-authored-by: oobabooga <112222186+oobabooga@users.noreply.github.com>
Adds a configurable Hugging Face model download cache location to Unsloth Studio, selectable from Settings, with per-cache download manifests, scoped deletion, and read-only inventory of previously selected caches.
* Studio: mask AMD GPU pins via ROCR so an unsupported iGPU can't crash llama-server
On a mixed AMD host (e.g. a discrete gfx1102 GPU next to a gfx1103 iGPU)
the bundled rocm-gfx110X llama.cpp build segfaults during HSA device
enumeration on the unsupported iGPU -- before llama-server prints a line,
so every model load fails with a bare signal and empty logs.
The GPU-subset pin masked visibility with HIP_VISIBLE_DEVICES, but HIP
filtering runs only after the HSA runtime has already enumerated (and
crashed on) every agent. Mask the subset via ROCR_VISIBLE_DEVICES (the
ROCr/HSA layer) instead, so a deselected/unsupported GPU is never
enumerated. Exactly one layer is masked (HIP cleared) to avoid the
double-mask reindex that would otherwise drop the child to CPU. The
whole-set tensor-split path and the CPU-only sentinel keep their existing
HIP behavior.
Also stop misreporting the resulting startup segfault as a vision
projector incompatibility: when the text-only mmproj retry also hard-
crashes with a signal, surface a GPU/driver init crash (with the ROCR
hint) instead of blaming the projector.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
* [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
* Tighten _emit_child_gpu_visibility comments for #7272
Comment and docstring only: condense the ROCR-vs-HIP masking rationale from ~22 to ~14 lines and the call-site note from 5 to 3, keeping every technical point (HSA enumeration segfault, physical ids, the -1 sentinel). Logic is unchanged, verified by an AST compare with docstrings stripped and by exercising _emit_child_gpu_visibility against a torch/HIP stub.
* Detect AMD SDK ROCm wheels (hip=None) in _emit_child_gpu_visibility (Codex P2)
The ROCm branch gated only on torch.version.hip, but AMD SDK wheels leave that unset while encoding 'rocm' in __version__ (detect_hardware handles this the same way). On such a wheel the masking was skipped entirely, leaving only CUDA_VISIBLE_DEVICES, so on a mixed AMD box the unsupported deselected iGPU still enumerated and could crash llama-server. Now the branch also treats 'rocm' in torch.__version__ as ROCm, mirroring detect_hardware. Adds tests for the hip=None SDK wheel (ROCR + default paths) and a CUDA guard so the version-string check can't false-positive.
* [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
* Remap CUDA_VISIBLE_DEVICES to post-ROCR ordinals on prefer_rocr for PR #7272 (Codex P1)
On the prefer_rocr path _emit_child_gpu_visibility set ROCR_VISIBLE_DEVICES to the
physical id and cleared HIP_VISIBLE_DEVICES, but left CUDA_VISIBLE_DEVICES at the
physical id. ROCR re-indexes the visible agents from 0 and, with HIP cleared, HIP
honours CUDA_VISIBLE_DEVICES -- so a non-zero pick (e.g. GPU 1) pointed out of
range, HIP saw 0 devices, and the child fell back to CPU, defeating GPU-picker
selections other than physical GPU 0. Remap CUDA to the post-ROCR ordinals
(0..N-1); GPU 0 is unchanged, the default (HIP) path and the CPU sentinel are
untouched, and non-AMD wheels never enter this branch.
* Detect AMD SDK wheels in _resolve_visible_physical_ids for PR #7272 (Codex P2)
* [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
* Keep the HIP mask on Windows ROCm in prefer_rocr for PR #7272 (Codex P2)
* Ignore ROCR_VISIBLE_DEVICES in _resolve_visible_physical_ids on Windows for PR #7272 (Codex P2)
* [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
* Preserve inherited ROCR masks in the tensor-split pin for PR #7272 (Codex P2)
---------
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
Co-authored-by: Daniel Han <danielhanchen@gmail.com>
Co-authored-by: Leo Borcherding <borchborchmail@gmail.com>
* Studio: reuse MLX prompt cache across turns instead of re-prefilling
* clean up
* key prompt cache on what the KV covers
* skip windowed KV caches past their window
* verify prefix coverage before caching KV
The first generation issued while the deferred compile is still in flight
can deviate transiently (observed once on a cold fp8 build: mean abs pixel
delta 0.063/255); once the graph is settled, same-seed same-batch-shape
images are bit-identical across runs.
Same-seed images at the same batch shape are bit-identical; a solo
regeneration with the recorded seed matches its batched rendition up to
batch-size-dependent kernel numerics (mean abs pixel delta about 2.5/255,
LPIPS delta under 0.002), not bit-exactly. The previous wording overclaimed
bit-identity across batch shapes.
Batched generation: /images/generate takes a prompts list (one image per
prompt, txt2img only) or a seeds list (one prompt, one image per seed);
the legacy batch_size path derives per-image seeds base..base+n-1 like
the native engine. Every image gets its own torch.Generator so any batch
member replays alone from its gallery recipe; the whole list runs as one
forward by default with OOM backoff that halves a failed chunk, and an
explicit batch_size caps images per forward. Validated 10-22x over
serial engines on 32-image suites with LPIPS deltas within 0.002.
Conditioning cache on the inference path: UNSLOTH_DIFFUSION_COND_CACHE_DIR
(the inference sibling of the trainers' cond_cache_dir, same persistent
store) wraps encode_prompt so repeated prompts skip the text-encoder
forward entirely; verified bit-identical outputs. Bypassed while LoRA
adapters are attached; tensor-argument calls pass through uncached.
Compile cache: GGUF loads fingerprint their own bundles (quant=gguf, a
different compiled graph than the dense family) and batched calls
register every distinct (w, h, batch) chunk shape they ran, so the heavy
GGUF batched warmups (~159 s at batch 32 on 12B-class, ~655 s on 20B
CFG-batched) are paid once ever.
GGUF loader: strip the sd.cpp model.diffusion_model. container prefix in
the single-file converter; diffusers' FLUX.2 converter KeyErrors on it
and the Qwen-Image identity mapping strands the model on meta.
* fix(rocm): prepend system ROCm libs on native Linux to avoid bundled HIP crash
Prebuilt llama.cpp bundles ship their own ROCR/HIP runtime which can be
incompatible with the host's amdkfd kernel driver, causing hsa_init()
to crash or report zero devices. The llama-server then silently falls
back to CPU while the UI reports GPU.
The existing workaround (_wsl_system_rocm_lib_dirs) that prepends
/opt/rocm/lib to LD_LIBRARY_PATH was gated on WSL (/dev/dxg) only,
leaving native Linux AMD hosts unprotected.
This commit adds _native_linux_system_rocm_lib_dirs(), a parallel
helper gated on:
- Linux platform (not WSL)
- /dev/kfd present (bare-metal AMD compute)
- Bundle contains bundled HIP libs (libggml-hip.so)
- System has libhsa-runtime64.so(.1)
It is called from both _llama_server_env_for_binary (serve-time)
and binary_env (install-time validation), directly after the WSL
block in both paths.
Fixes#7208Fixes#7208
* Add UNSLOTH_LLAMA_NO_SYSTEM_ROCM opt-out to native-Linux system ROCm preference for PR #7233
Lets a host where the bundled runtime works but system ROCm is mismatched keep
the bundle. Mirrored in llama_cpp.py and install_llama_prebuilt.py.
* Prefer env-configured ROCm root over /opt/rocm fallback for PR #7233
Put HIP_PATH/HIP_PATH_57/ROCM_PATH-derived roots before /opt/rocm so a stale
/opt/rocm can't shadow the driver-matching install the env vars point at.
Mirrored in llama_cpp.py and install_llama_prebuilt.py.
* Match versioned libggml-hip.so via glob so the native-Linux ROCm fix fires for PR #7233
* Clarify native-Linux ROCm prepend uses the consistent system stack for PR #7233
* llama_cpp: tighten native-Linux ROCm prepend comments (no code change)
---------
Co-authored-by: Daniel Han <danielhanchen@gmail.com>
* Studio (Windows): keep prompt caching on full GPU offload (#5692 follow-up)
The #5692 full-offload tuning also added --no-cache-prompt, which disables
in-VRAM prompt-prefix reuse. That is unrelated to the host-RAM KV checkpoints
#5692 fixed (--cache-ram 0 / --ctx-checkpoints 0): a fully offloaded model keeps
its KV cache in VRAM, so reusing a common prefix does not copy to system RAM and
does not cause the PCI-E overhead. --no-cache-prompt only forces every request to
re-prefill the whole prompt, which is small for short chats but severe for large
stable system prompts reused across calls (coding agents, long multi-turn chats).
Remove --no-cache-prompt; keep the checkpoint disables and the thread/OMP tuning.
_prompt_cache_disabled stays False (its default), so slot save/restore is intact.
Verified on a fully offloaded gemma GGUF: an identical repeated prompt reprefills
1 token instead of 2220.
* Guard against re-adding --no-cache-prompt to any llama-server command
Add a backend-wide test that AST-scans studio/backend and fails if
--no-cache-prompt is appended/extended/+= into a command. This locks in
the #7260 fix across every code path, not just load_model. Detecting the
flag or honouring a user-supplied one stays allowed.
* [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
---------
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
* Studio: make Stop and stall deadlines interrupt a wedged stream portably
The cancel watcher unblocks a stalled read by shutting the socket down from
another thread, which works on POSIX but not reliably on native Windows, where
Winsock does not dependably wake a recv() already in progress on another thread.
Wrap the httpcore network stream so the reader loops each read in short slices
and polls the cancel event itself. Stop and the stall deadlines now interrupt a
wedged mid-stream read without any cross-thread socket teardown, and a slow but
still-alive stream is never torn down. The POSIX shutdown path is preserved.
* [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
* Honor the post-first-token stall timeout in the cancel-aware read
httpcore snapshots request.extensions timeout read once when the body
starts, so lowering it to the stall timeout after the first token never
reached the socket read and a one-token-then-silent server hung for the
full prefill window. Re-read the live extensions timeout per call and
bound each read by it, falling back to the httpcore-passed timeout when
absent so prefill and normal completion are unchanged.
* [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
* studio: tighten comments in the llama.cpp stall timeout path
* Tighten comments in the stream stall cancel path
---------
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
Co-authored-by: danielhanchen <unslothshared@gmail.com>
nf4 loads now enable double quantization (~0.4 bits/param off the frozen base
scales at no fidelity cost), fp8 training uses the rowwise recipe when the
torchao build ships it (per-row scaling confines the DiT activation outliers
that a tensor-wide scale collapses), and the inference quant filter gains a
per-scheme GEMM-tiling divisibility floor (16 for scaled_mm, 32 for MX blocks)
so one ragged Linear cannot crash the first denoise after a clean quantize
pass. plans/fsdp2_diffusion_design.md records the multi-GPU design: bf16/fp8
over FSDP2 with per-block units, LoRA attached before sharding, int8 out of
scope (DTensor over the quantized subclass is undefined), per-family notes.
* Studio: persist llama.cpp KV cache across idle auto-unload (slot save/restore)
* [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
* Studio: address KV persistence review feedback
* Studio: guard KV restore on launch config
* Studio: fix KV resume purge race, fingerprint requested ctx, purge on disable
* [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
* Studio: re-check idle/keep-KV settings after slot save, ns file identity
* Studio: shard-aware KV guard, honor user --no-cache-prompt, early save cap
* [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
* Studio: honor LLAMA_ARG_CACHE_PROMPT env in slot-save guard
* Studio: derive prompt-cache state from final argv for slot saves
* Studio: stat LoRA/control-vector sidecars in KV restore fingerprint
* [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
* Studio: parse csv and FNAME:SCALE sidecar syntax in KV fingerprint
* Studio: address codex review on idle-unload KV resume
* [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
* Studio: harden slot-save cleanup, cap accounting, stale-KV guard, save timeout
* [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
* Studio: treat unavailable KV estimate as full-cap for slot-save disk check
---------
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
Co-authored-by: Daniel Han <danielhanchen@gmail.com>
* Studio: GPU memory dropdown — llama.cpp --fit on and manual gpu-layers/cpu-moe
* Studio: simplify GPU memory changes (reuse ParamSlider, GPU_LAYERS_ALL, loadedGpuMemoryFields helper)
* Studio: GPU picker — choose which GPUs a GGUF model loads on (gpu_ids)
* Studio: simplify GPU picker (share /api/system fetch, validate gpu_ids)
* Studio: GPU picker review fixes (gate relative indices, no cross-model leak, validate, types)
* Studio: group GPU controls under a collapsible GPU section
* Studio: GPU feature review fixes (fix fit-ctx test, behavior-test the floor, comment accuracy)
* Studio: make GPU a top-level settings section (not nested under Model)
* Studio: flatten GPU controls into the Model section, group by GPU/context/generation
* Studio: move GPU Memory to the bottom of Model with its dependent controls beneath it
* Studio: move GPU Memory below Tensor Parallelism and GPUs below GPU Memory
* Studio: tighten GPU Memory and GPU Layers tooltip copy
* Studio: fix fit-mode context slider track-click, restore GPU Memory tooltip, shorten fit dropdown label
* Studio: GPU Memory tooltip one mode per line, briefer
* Studio: note HIP_VISIBLE_DEVICES (ROCm) in the GPUs picker tooltip
* Studio: narrow the GPU Memory dropdown to fit the shortened label
* Studio: use 'llama.cpp --fit' in the GPU Memory tooltip for consistency
* Studio: allow Tensor Parallelism in Manual GPU mode
* Studio: graduated MoE-on-CPU offload (--n-cpu-moe) replacing the all-or-nothing toggle
* Studio: size the MoE-offload slider for staged (deferred-load) models
* Studio: share one GGUF header walk for the context-length and MoE-count readers
* Studio: size the GPU Layers slider for staged models (one staged-header read)
* Studio: move Tensor Parallelism below the GPUs picker
* Studio: GPU split (--tensor-split) per-GPU model share in Manual mode
* Studio: tolerate whitespace in GPU split input, move it below GPU Layers
* Studio: rename the GPU split control to "Split ratio"
* Studio: Split ratio sends explicit even input; fix blank=free-VRAM (not even) copy
* Studio: tighten llama.cpp --fit VRAM margin with --fit-target 512
* Studio: GPU memory review fixes (rollback re-baseline, single-GPU TP gate, accurate copy)
* [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
* Studio: move Split ratio below MoE Layers on CPU
* Studio: address PR review (fix GPU-info hydration race, share fit context-length across load paths)
* Studio: address codex review (manual single-GPU TP guard, GPU-aware spec defaults in fit/manual, GGUF-only context/preference)
* Studio: address codex review round 2 (gpu_present seed, single-GPU tensor-split guard, staged manual-knob reset, strip inherited offload flags)
* Studio: address codex review round 3 (strip inherited --n-cpu-moe, CPU-fallback warning in Manual mode)
* [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
* Studio: address codex review round 4 (preserve pinned fit context across a later Apply)
* Studio: address codex review round 5 (honor GPU picker for diffusion GGUFs, clear fit pin on cross-model switch)
* Studio: preserve the pending GPU Memory mode when staging a model
* Studio: pin diffusion GPU device order and reset GPU-memory state for diffusion loads
* Studio: address codex review round 6 (fit-Auto rollback context, preserve manual non-tensor split modes, persist GPU mode on load not select)
* Studio: persist the applied GPU Memory mode, not the requested one (skip diffusion loads)
* Studio: replace Manual-mode split-ratio field with per-GPU layer sliders
* Studio: clarify per-GPU layer split hint for tensor-parallel mode
* Studio: address codex review round 7 (allow GGUF gpu_ids past the legacy guard, replay GPU-memory fields on respawn)
* Studio: address codex review round 8 (size the validate preflight like the load in fit mode, across both load paths)
* Studio: skip the training-OOM guard for llama.cpp --fit GGUF loads (they spill to RAM)
* Studio: drop the now-redundant compare-path validate sizing (the --fit guard skip makes it moot)
* Studio: address codex review round 9 (keep the training guard for fit loads, forward gpu_ids to validate, strip inherited manual tensor-split)
* Studio: address codex review round 10 (gate GPU-memory adoption on is_gguf, record manual knobs only in Manual mode)
* Studio: handle diffusion GGUFs symmetrically in the GPU Memory controls (preserve the standing mode preference, hide the inapplicable mode/TP controls)
* Studio: remember the GPU Memory settings per model
* Studio: consolidate --fit mode and Manual mode into a single Manual mode
* Studio: preserve the per-GPU layer split across GPU Layers changes
* Studio: trim overly long GPU Memory comments
* [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
* address GPU memory config review comments
* trim redundant GPU memory tests
* [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
* Reconcile manual-mode TP drops with the #6659 drop-site invariants
* Preserve quantized KV in manual --fit, charge GGUF companions in full, reconcile GPU pick on load
* [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
* Clear stale GPU baseline on non-GGUF loads so it can't read as dirty
* Fix no-context-shift test for the conditional -c flag
* Credit manual GPU-layer offload for cached HF GGUFs
* Reset per-model load knobs on GGUF quant switch
* [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
* Strip inherited tensor-split when manual ratio is cleared
* Match auto-load validation to safetensors placement
* Reset editable manual knobs after Auto GGUF loads
* Record a single device for diffusion GPU picks
* Reset per-model GPU knobs before applying saved settings
* Address review comments
* [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
* Guard manual tensor splits and keep remembered context on auto-load
* [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
* Snapshot compare knobs, seed splits from free VRAM, flag zero-offload loads
* [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
* Exempt CPU-only loads from the guard floor and harden compare and reseed paths
* [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
* Reach full offload from the layers slider and charge extras drafters in the guard
* [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
* Warm the GPU device cache before pick reconciles and disable staged GPU controls
* Align the training guard with inherited extras, spec mode, and compare targets
* [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
* Hide GPUs from companion-less zero-offload loads
* [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
* Size diffusion picks per device, own manual offload flags, reject XPU picks
* [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
* Drop tensor flags at zero layers and exempt CPU-pinned drafters
* [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
* Allowlist the zero-layer tensor parallel drop site
* Keep validate and load guards on the same extras and refresh stale baselines
* [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
* Drop mismatched manual tensor splits before launch
* [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
* Gate XPU picks on the real backend field and harden split and hydration paths
* [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
* Weight full GPUs as zero, clamp split shares, and refine the zero-layer mask gate
* [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
* Carry fit context across mode changes and align drafter and picker gates
* [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
* Catch variant switches, uncached diffusion repos, and text-only mmproj skips
* [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
* Check companions on the first device and size native and remote zero-layer loads
* [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
* Replace the training guard's precise VRAM modeling with a conservative bound
* Baseline context pins on non-GGUF hydration and reprobe list-seeded staged GGUFs
* [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
* Size manual splits by their largest share and preserve resolved context from Default
* [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
* Default-deny unsized required companions and price KV at the effective cache dtype
* [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
* Reserve MTP draft KV and MLA target-copy in the training guard
* [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
* Size tensor-parallel loads per device and show GPU controls for native GGUFs
* [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
* Reserve MTP overhead for uncached remote GGUFs and the mmproj runtime factor
* [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
* Drop the training-coexistence VRAM estimation this PR added
* [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
* Gate remembered load settings to GGUF picks
* Lock the remaining load-time controls during a staged load
* Clear the stale native-path token on compare loads
* Drop a stale guard reference from the zero-offload masking comment
* Seed GPU baselines from the rollback response and drop never-emitted offload flags
* Match validate's training guard to load and keep the native reload token
* [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
* Trim verbose GPU-memory comments
* Thread the variants header walk off the event loop, honor device pins on zero-offload, and hold staged GPU edits
* [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
* Honor manual placement and classify pinned zero-offload loads
* Close diffusion admission and status hydration gaps
* [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
* Check the actual diffusion GPU during training
* Align staged baselines and manual reload dedupe
* Fix GGUF placement and rollback state
* Harden manual GGUF placement boundaries
* [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
* Remove unused resolve_tensor_parallel import in llama_cpp.py
The name is used only in llama_server_args.py, routes/inference.py, and tests,
not in llama_cpp.py; the unused hoisted import trips the import-hoist verifier
in the source-lint CI job.
* Fix diffusion GPU dedup and training guard for non-numeric device tokens
The diffusion runner drives only its single lowest device and the backend
records that one device (self._gpu_ids = [sorted(gpu_ids)[0]]), but the reload
dedupe compared it against the full requested list, so a multi-GPU pick that
resolves to the same device forced a needless reload. Normalize the request the
same way for a loaded diffusion model in both _already_in_target_state and the
route _request_matches_loaded_settings.
The chat-during-training coexistence guard called int() on the single-device
token and hard-rejected when it could not parse. A non-numeric token (a CUDA
UUID / MIG handle) now sizes against the whole visible pool like the GGUF guard
instead of falsely blocking the load, and an empty token (a CPU-only runner such
as a CPU diffusion GGUF) is allowed outright since it uses no GPU VRAM.
* Tighten comments added by the GPU memory config changes
* Harden GGUF placement from independent review: VRAM sizing, diffusion TP reset, tensor_split validation
- Training coexistence guard: a single-device runner pinned through an
unresolvable UUID/MIG token was sized against the aggregate visible-VRAM pool,
so a load could pass on capacity it cannot use and then OOM active training.
Size against the worst-case visible device (min free) instead, keeping the
guard's documented default-deny contract. The empty-token (CPU-only runner)
allow path is unchanged.
- Diffusion startup: _start_diffusion_server now resets self._tensor_parallel to
False alongside the other placement resets. A prior tensor-parallel chat load
(process killed but not fully unload-reset) otherwise left /status misreporting
tensor parallelism and made an identical diffusion re-Apply reload against the
stale state.
- tensor_split: reject negative / non-finite / all-zero splits up front. They
were dropped at launch but still compared raw in the reload dedupe, so an
identical Apply reloaded indefinitely.
- Tests: the shared httpx stub was incomplete and, installed via setdefault
before real httpx loaded, broke a combined pytest run (collection errors on
httpx.Response). Import the real installed httpx instead.
* [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
---------
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
Co-authored-by: danielhanchen <unslothshared@gmail.com>
Co-authored-by: danielhanchen <danielhanchen@gmail.com>
* Studio: hide infra models from the hub cached inventory
The hub inventory scans behind /api/hub/cached-gguf and /api/hub/cached-models
returned the llama.cpp install validation probe (ggml-org/models) and the RAG
embedder (unsloth/bge-small-en-v1.5[-GGUF]) as on-device models. Share the
hidden-model check from routes/models.py via utils/models/hidden_models.py and
apply it in both scans. A GGUF infra repo stays visible when the user
explicitly downloaded a variant through the Hub, since variant manifests only
exist for user-initiated downloads.
* [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
* Studio: make On Device trust the hub inventory, match repo ids exactly, lighten the hidden-model import
Follow-up on the hub cached-inventory hidden-model change, addressing the review.
On Device now trusts the Hub inventory API for cached rows. The backend already
hides the RAG embedder and the llama.cpp probe and re-includes a GGUF infra repo
once the user downloads a variant through the Hub, but the frontend was
re-hiding it by repo id, so the user-downloaded variant never appeared in the On
Device list or the count. isVisibleInventoryRow now short-circuits cached rows
(kind === "cache") to visible and keeps client-side needle hiding only for local
filesystem rows and Discover.
is_hidden_model matches Hub repo ids exactly (case-insensitive) against the probe
plus the effective embedder and its GGUF companion, instead of substring
matching the configured-embedder basename. A custom embedder with a generic
basename like org/model no longer hides unrelated cached repos such as
user/model-chat or org/model-instruct. The probe filename and local-path
embedders keep exact matching.
The helper moves to utils/hidden_models.py and is imported at module scope in the
hub cache scanner, so it no longer pulls in utils/models/__init__ (the eager
model-config/checkpoint stack) and a broken import fails at startup instead of
being swallowed per-repo and silently emptying the inventory. routes.models
keeps the _is_hidden_model and _safe_resolve aliases and drops the unused
_HF_REPO_ID_RE re-export that was failing source lint.
Tests: exact repo-id matching with a custom embedder, the cached-models scan
keeping an unrelated repo, and a clean-interpreter check that the helper imports
without the model-config stack.
* Studio: match the llama.cpp probe filename on both path separators
The hidden-model check compared the probe's on-disk filename with
Path(value).name, which on a POSIX interpreter does not split a Windows-style
path ("...\stories260K.gguf") and would let the probe through. Split on both
separators so the probe is matched regardless of which OS produced the path,
matching the tolerance of the previous substring check. Adds a Windows-path
assertion to the probe test.
* Studio: harden hidden infra model handling
* Fix hidden cache row confirmation
* Fix hidden local rows and confirmed hint merges
* [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
* Handle snapshot-configured hidden models
* Hide basename-only default embedders
* Fix dynamic embedder inventory filtering
* Studio: hide the configured RAG embedder from Discover and feed rows
---------
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
Co-authored-by: danielhanchen <unslothshared@gmail.com>
Co-authored-by: Daniel Han <23090290+danielhanchen@users.noreply.github.com>
* Replace standalone Studio wording with Unsloth
Replace the single word Studio with Unsloth wherever it is used as
shorthand for Unsloth Studio in docs, CLI output, UI strings, i18n
locales, workflow display names, comments and docstrings.
Kept unchanged: the full name Unsloth Studio, third party product
names (LM Studio, Visual Studio, Mac Studio), feature names
(Recipe Studio, Fine-tuning Studio and its translations), and all
identifiers such as env vars, commands, paths and filenames.
* Address review feedback on the Studio wording rename
Use "an" before Unsloth where the rename left the article as "a".
Restore the split brand where Unsloth and Studio render as two halves
of the full product name: the onboarding sidebar subtitle and the
IPv6 localhost warning. Scope two messages to the full name Unsloth
Studio where plain Unsloth was misleading: the AMD README bullet and
the CLI studio setup error.
* fix(studio): add MLX adapter state control
* fix(studio): honor MLX adapter comparison state
* fix(studio): keep enabled MLX adapters permissive
* Studio: preserve public error message on MLX compare-mode adapter failures
generate_with_adapter_control raised a plain RuntimeError, which the compare
route handled with the generic handler that drops the operational message.
Raise GenStreamErrorRaised(public=chunk.public) instead and catch it in the
streaming and non-streaming consumers, matching the safetensors tool loop, so
errors like 'model is being unloaded' surface their real message.
* Studio: re-emit VLM think prefill inside the adapter context
The compare-mode merge dropped _generate_vlm's upfront yield of the prefilled
<think> block. Restore it as the first snapshot inside the lock+adapter context
(matching _generate_text) so the UI renders the thinking block during prefill
and a cancel/error before the first token does not drop it. Adds a regression
test asserting the prefill is emitted first, after entering the adapter context.
---------
Co-authored-by: danielhanchen <unslothshared@gmail.com>
The Connections form hid the API key field for the Ollama preset, which
blocked Ollama cloud (it requires a key). Show the optional field for
Ollama; the backend already sends Authorization: Bearer when a key is
set and omits the header when empty, so local keyless servers are
unaffected.
Fixes#7163
torchao's Float8Tensor KernelPreference defaults to AUTO, which switches
the weight-quantize kernel to MSLK whenever an mslk package is importable
on sm90+. Measured on B200: that changes fp8 scale rounding bitwise (8/8
FLUX matrices differ, scales ~55 percent of bytes), so a box that merely
gains mslk would break the hosted-prequant bit-identity invariant; the
mslk path is also slower under torch.compile (opaque extern call blocks
inductor's quantize fusion, FLUX.1 fp8 e2e 1.149 to 1.624 s). Pin
KernelPreference.TORCH explicitly, matching current no-mslk behaviour
bit for bit; signature-gated for older torchao. GPU-smoked (finite,
rel err 0.037) and pinned by test.
The 22B distilled DiT was trained against ltx_core's fixed
DISTILLED_SIGMA_VALUES, but the diffusers scheduler derives 8-step
spacing from resolution-shifted flow matching and lands far off at
every reachable mu (second sigma 0.945-0.981 vs 0.99375, tail
0.37-0.61 -> 0.1 vs 0.725 -> 0.42 -> 0). At the distilled default step
count the backend now passes the list verbatim, neutralising the
scheduler's dynamic shift and terminal stretch for the call (they
distort even explicit sigmas) and restoring them afterwards. Other
step counts and the dev/base DiT keep the scheduler's own spacing.
Live-verified on B200 through the video branch backend: the scheduler
holds the exact curve after an 8-step distilled GGUF generation, config
restored, healthy clip. Also reword the transformer_quant resolved
reason to the measured reality: quant halves resident weights and
hosted checkpoints cut load time, while per-step speed is roughly bf16
parity.
The dtype override swapped encoder.__class__ to a dynamic subclass, which
breaks transformers' kwargs-based output recording: a fp8-cast
Qwen3VLModel stopped returning hidden_states and every krea-2 generation
with text_encoder_quant=fp8 crashed at encode_prompt (regression from the
HiDream TE4 change; caught by the krea hosted-TE live smoke). The
override is now a property shadowed on the ORIGINAL class that prefers a
per-instance compute-dtype attribute, so class identity is preserved and
uncast instances keep the stock behaviour. The idempotency test now pins
exact class identity and the uncast-sibling fallback.
Daniel Han