Keep committed request inputs protected from age recovery until exact release ends their ownership. Startup-scanned files remain reclaimable and can acquire ownership through reservation.
Assisted-by: Codex:gpt-6
Pin each release path component before removing request-owned inputs and sidecars. Stop pruning when a directory identity changes.
Assisted-by: Codex:gpt-6
Share capacity accounting across HTTP and S3 request inputs so workers
reject uploads before exhausting their filesystem. Reconcile exact release
and crash recovery with the same guard.
Assisted-by: Codex:gpt-6
Concurrent staging can otherwise exceed its byte limit or consume reserved filesystem headroom. Explicit states keep bytes charged through each reservation, write, and commit transition.
Use a synchronized waiter count to prove Commit blocks until bounded writers close, and retain committed baselines across re-reservation.
Assisted-by: Codex:gpt-6
Ephemeral inputs remained on workers after inference completed. Release each exact key after synchronous and streaming calls, including partial staging failures.
Use a bounded cleanup context so caller cancellation cannot suppress release. Preserve caller requests and backend results when cleanup fails.
Assisted-by: Codex:gpt-6
Request inputs need transport-neutral cleanup after backend calls. Add authenticated exact-key deletion for HTTP and coordinated cache eviction before shared-object deletion for S3/NATS.
Preserve URL metacharacters as filename data, reject unsafe keys, and remove upload sidecars while pruning empty request directories.
Assisted-by: Codex:gpt-6
Time-based retention can still fill a worker under bursty or high-rate input. Define request-lifecycle cleanup with capacity reservation and crash recovery.
Assisted-by: Codex:gpt-6
High-frequency camera and audio inputs can fill a worker before the current six-hour cleanup window expires.
Define a one-hour retention policy that preserves recently modified request payloads.
Assisted-by: Codex:gpt-6
* fix(gallery): default audio-cpp models to backend:best
The audio-cpp engine creates its session on the CPU backend when no
backend option is given, so every gallery model ran CPU-only even on
machines where a CUDA/Vulkan/Metal device was registered. backend:best
selects the best available backend and falls back to CPU.
Assisted-by: Claude:claude-fable-5
Signed-off-by: Plamen K. Kosseff <p.kosseff@gmail.com>
* docs(audio-cpp): explain gallery device selection
Document automatic compute backend selection and the CPU override.
Assisted-by: Codex:gpt-6
Signed-off-by: Plamen K. Kosseff <p.kosseff@gmail.com>
---------
Signed-off-by: Plamen K. Kosseff <p.kosseff@gmail.com>
Co-authored-by: localai-org-maint-bot <306269227+localai-org-maint-bot@users.noreply.github.com>
The device fell back to CPU unless the model config set cuda: true,
while MPS right below was auto-detected — GPU hosts silently rendered
on CPU for any gallery entry missing the flag. Use CUDA whenever torch
reports it available (ROCm builds included), keep cuda: true as an
explicit force, and allow pinning with the device: model option (e.g.
options: ["device:cpu"]). Gallery entries stay untouched.
Assisted-by: Claude:claude-fable-5
Signed-off-by: Plamen K. Kosseff <p.kosseff@gmail.com>
Virtual model names have no primary file to anchor the worker path.
Companion assets still stage successfully, but relative options retain
an incorrect model directory and fail to load.
Derive the worker root from successfully staged option assets when the
primary path is absent. Cover Buffalo packs, files, directories,
overrides, and failed transfers. Document the frontend upgrade.
Assisted-by: Codex:gpt-6 golangci-lint
Co-authored-by: Ettore Di Giacinto <mudler@localai.io>
A worker can retain all model bytes with an unfinished-upload marker.
Retries then start at zero and repeatedly fail with HTTP 416.
Verify the existing bytes and finalize same-file retries at full size.
Reuse the normal integrity checks so corrupt content cannot be accepted.
Add regression coverage and document worker recovery.
Assisted-by: Codex:gpt-6 golangci-lint
Co-authored-by: Ettore Di Giacinto <mudler@localai.io>
Accept original embeddings and timestamps so clients can restore faces
when the in-memory store restarts. Derive stable IDs from exact vectors
to make registration retries preserve identity without duplicate entries.
Assisted-by: Codex:GPT-6 golangci-lint
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
Co-authored-by: Ettore Di Giacinto <mudler@localai.io>
* fix(distributed): stage sound detection audio
Sound detection passes frontend temporary paths directly to remote
workers, unlike transcription. Stage the WAV before classification so
CED can read it without a shared temporary directory.
Preserve the original request for retries and propagate staging errors
without calling the backend. Cover staging, request preservation, and
error handling with regression tests.
Assisted-by: Codex:GPT-6 golangci-lint
* test(distributed): verify routed sound staging
Call sound detection through the client returned by SmartRouter.Route.
This checks interface dispatch through both routing wrappers, rather
than constructing FileStagingClient directly.
The test fails without the sound-staging override and passes with it.
Assisted-by: Codex:GPT-6 golangci-lint
---------
Co-authored-by: Ettore Di Giacinto <mudler@localai.io>
Community-maintained packagings that currently track releases —
Homebrew, ALT Sisyphus and the Gentoo local-ai overlay — with a note
that versions may lag. Placement and scope as discussed in the issue.
Assisted-by: Claude:claude-fable-5
Signed-off-by: Plamen K. Kosseff <p.kosseff@gmail.com>
* ⬆️ Update leejet/stable-diffusion.cpp
Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
* fix(stablediffusion): adapt streaming options
Upstream now selects segmented weight streaming automatically and removes the stream_layers field. Keep the old LocalAI option as a no-op for existing model configurations.
Assisted-by: Codex:gpt-5
---------
Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
Co-authored-by: Ettore Di Giacinto <mudler@localai.io>
* ⬆️ Update antirez/ds4
Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
* fix(ds4): link upstream image helpers
The ds4 bump adds vision calls to the engine object. Link the new image preprocessing object into every backend target.
Assisted-by: Codex:gpt-5
---------
Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
Co-authored-by: Ettore Di Giacinto <mudler@localai.io>
* Update containers.md to fix podman image qualification
Signed-off-by: Alex Mazzariol <alex@alex-maz.info>
* docs(containers): clarify Podman image names
Podman can reject short image names when no registry is configured. Explain why the examples use fully qualified Docker Hub names.
Assisted-by: Codex:gpt-5.6
---------
Signed-off-by: Alex Mazzariol <alex@alex-maz.info>
Co-authored-by: localai-org-maint-bot <306269227+localai-org-maint-bot@users.noreply.github.com>
Qwen3-style chat templates append the opening <think> tag to the *prompt*
when thinking is enabled. The model therefore never generates it and emits
only the reasoning text plus the closing </think>.
sglang's ReasoningParser keys off the opening tag:
in_reasoning = self._in_reasoning or self.think_start_token in text
if not in_reasoning:
return StreamingParseResult(normal_text=text)
so with such a template the entire completion — reasoning and answer, the
raw </think> in between — is returned as content and reasoning_content
stays empty, no matter how reasoning_parser is configured.
sglang's own OpenAI server handles this via
force_reasoning = (self.template_manager.force_reasoning
or self._get_reasoning_from_request(request))
This backend has no template manager, so derive the same signal from the
rendered prompt: if it ends with the detector's think_start_token, the tag
was prefilled and the parser is constructed with force_reasoning=True.
Structured decoding is the exception, and it matters: a grammar applies
from the first token, so the model cannot emit the closing tag even though
the template opened the block. The whole completion is schema output and
belongs in content — forcing there files it as reasoning and returns an
empty answer. Measured against a JSON-schema code audit: 10107 characters
of "reasoning", zero content. sglang's own server keeps the two apart for
the same reason; its grammar backend owns the reasoning prefix when a
reasoning parser is configured.
force_reasoning is only passed when it is meant to be True, so detector
defaults (DeepSeek-R1 already defaults to True) are untouched, and a
prompt without a prefilled tag behaves exactly as before — which matters,
because forcing unconditionally makes an answer generated with thinking
off disappear into reasoning_content.
The construction is factored into _new_reasoning_parser() so the streaming
and non-streaming paths, which previously built the parser separately,
cannot drift apart.
Signed-off-by: pos-ei-don <1822533+pos-ei-don@users.noreply.github.com>
With `template.use_tokenizer_template: true` the sglang and vllm backends
render the prompt themselves via `tokenizer.apply_chat_template()`, and they
hand it plain string content. A chat template only emits the model's own media
tokens when the content is a list of parts, so the rendered prompt carries no
`<|vision_start|><|image_pad|><|vision_end|>`. The pixels do reach the engine
(`image_data` / `multi_modal_data`), but both engines locate them by scanning
the prompt for that token, so they are discarded silently: HTTP 200, no
warning, and the model answers as if no image had been attached.
Add `attach_media_parts()` to the shared `python_utils` helper and call it in
both backends: the last user turn is rebuilt as
`[{"type": "image"} * n, {"type": "video"} * n, {"type": "text", ...}]` before
templating, which makes the template emit the placeholders. The pixels keep
travelling out of band exactly as before.
Text-only requests are untouched - with no media the helper returns None and
the original string-content path runs unchanged. If a template cannot iterate
content parts (a text-only model), the parts render is caught and the request
falls back to the previous string-content prompt instead of failing.
Signed-off-by: Tai An <antai12232931@outlook.com>
vLLM's engine-based reasoning parsers derive their initial state from the
chat template kwargs. Qwen3Parser:
chat_kwargs = kwargs.get("chat_template_kwargs", {}) or {}
self.thinking_enabled = chat_kwargs.get("enable_thinking", True)
Constructed as ReasoningParser(tokenizer) the flag defaults to True, so the
parser starts in the REASONING state. A completion produced with thinking
disabled contains no tags at all, and every reasoning parser shape then
reports the whole answer as reasoning:
- engine-based parsers classify it by initial state;
- BaseThinkingReasoningParser hits its documented "may not generate start
token" fallback and returns (model_output, None).
Either way `content = c if c is not None else generated_text` turns that
into a duplicate: a Qwen3 model answering "391" with thinking off comes back
as reasoning_content="391" AND content="391".
Measured against Qwen3.5-MoE on vLLM 0.28, non-streaming:
before thinking on reasoning=202 content="391"
thinking off reasoning="391" content="391" <- duplicated
after thinking on reasoning=192 content="391"
thinking off reasoning="" content="391"
Forward the kwargs the prompt was rendered with, which is what vLLM's own
OpenAI server does; parsers that do not accept the argument keep the plain
constructor.
_split_reasoning() covers the older parser shape, which has no initial state
to set. It only reclassifies when the parser exposes a start/end token pair
and neither the completion nor the prompt ever opened a reasoning block.
Truncated reasoning (block open, end token never arrived) stays reasoning,
and parsers without that token pair are left untouched.
Signed-off-by: pos-ei-don <1822533+pos-ei-don@users.noreply.github.com>
Ettore Di Giacinto