The CUDA 13 FlashAttention build still exhausts hosted-runner memory with a single ninja worker because nvcc can compile multiple threads internally. Limit nvcc to one thread for that profile and guard the setting in the backend test script.
Assisted-by: Codex:gpt-5
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
grpc::ServerWriter::Write() returns false once the peer is gone, and
PredictStream ignored that result at every call site. The handler kept
pulling decoded tokens and writing them into a dead stream, so the
llama.cpp slot stayed busy until the generation ended on its own terms.
A model configured with max_tokens 0 and a large context ends on its own
terms only at the context limit. On a 35B model at ~41 t/s a 120k context
is about fifty minutes, and a slot held that long is a slot every other
request for that model queues behind. Two abandoned requests were enough
to make a node with free VRAM and a healthy control plane serve nothing:
new requests timed out waiting for a slot, each timeout abandoned another
generation, and the node fell further behind the longer it ran.
Track the peer instead. The first failed write retires it for good, since
a stream never recovers, and the RPC's own cancellation flag folds into
the same predicate so the loop has one condition to test. Returning early
is what frees the slot: ~server_response_reader() posts
SERVER_TASK_TYPE_CANCEL for whatever is still decoding.
TTSStream already checked Write(); this brings PredictStream in line.
Cancellation stays cooperative and is checked between decoded results, so
a batch already in flight may finish before the request stops.
Assisted-by: Claude:claude-opus-5
SciPy 1.18 requires Python 3.12 or newer. Keep this backend on a
compatible portable Python for Linux and macOS builds.
Assisted-by: Codex:gpt-5.6 [Codex]
(cherry picked from commit 70bf6d4a3a)
Adds FunASR/SenseVoice as a Python backend for speech-to-text with
support for CPU, CUDA 12/13, ROCm, Intel SYCL, L4T, and Apple MPS.
Co-authored-by: xingyifeng <xingyifeng@users.noreply.github.com>
Saved profiles previously resolved to one audio path and transcript, so
cloning backends could not use several examples of one personality.
Store ordered audio and transcript pairs while preserving the legacy
first-reference fields. Fish Speech and audio.cpp receive all pairs,
including on distributed workers. Other backends retain their
single-reference behavior.
Assisted-by: Codex:gpt-5
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
The generated gRPC source tree omitted the new header and test. Every llama.cpp-derived backend therefore failed when grpc-server.cpp included the missing header.
Assisted-by: Codex:gpt-5.6 [systematic-debugging]
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
llama.cpp reports the same tensor-count error for unsupported model layouts and damaged GGUF files. Add a focused hint so operators can update the backend or verify the model without losing the upstream diagnostic.
Assisted-by: Codex:gpt-5.6
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
The editable install records the backend build path, which does not exist after LocalAI relocates the packaged backend. Add the runtime source directory to PYTHONPATH so inference modules remain importable.
Assisted-by: Codex:gpt-5
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
The HIP build reaches ggml configuration and requires the rocBLAS CMake package. Install its development package with the existing hipBLAS dependency.
Assisted-by: Codex:gpt-5
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
audio.cpp forwards GPU_TARGETS to CMake as a semicolon-delimited list. The comma-delimited LocalAI value was treated as one invalid HIP architecture during configuration.
Assisted-by: Codex:gpt-5.6-sol
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
The ROCm builder lacks the CMake package metadata that ggml requires. Install the development package only for hipBLAS builds.
Assisted-by: Codex:gpt-5
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
The pinned audio.cpp revision supports HIP, but LocalAI neither builds a ROCm image nor accepts its backend option. AMD hosts therefore fall back to the CPU image.
Build and publish the HIP variant, connect it to AMD capability selection, and accept both upstream HIP names.
Assisted-by: Codex:gpt-5
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
Expose diffusers audio pipelines through the existing sound-generation RPC. AudioLDM2 can now return PCM WAV output from the model gallery without a separate backend.
Assisted-by: Codex:gpt-5
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
The pinned mlx-video package requires Python 3.11 or newer, while an empty PYTHON_VERSION selected the backend helper default of 3.10. Pin the available 3.11.13 portable runtime for the Darwin package build.
Assisted-by: Codex:gpt-5
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
Add a Darwin-only MLX-Video backend for LTX-2 and converted Wan checkpoints, expose it through the existing video API, and wire packaging, discovery, tests, docs, and an example.
Assisted-by: Codex:gpt-5
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
Prefer an explicitly configured Triton assembler, otherwise use the executable ptxas from CUDA_HOME so torch.compile can target GPU architectures newer than Triton bundled tooling.
Assisted-by: Codex:gpt-5
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
Keep the relocated upstream source importable, select CUDA 13 PyTorch wheels instead of the aarch64 CPU fallback, and decode reference audio without torchcodec, which has no Linux arm64 wheels.
Assisted-by: Codex:gpt-5
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
The standalone Python release used by libbackend does not publish a 3.11.18 artifact. Pin Whisper-Medusa to the available 3.11.13 build and cover the generated download URL.
Assisted-by: Codex:gpt-5 [systematic-debugging]
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* fix(faster-whisper): manually install ctranslate2 with rocm support before installing other dependencies
Signed-off-by: Andreas Egli <github@kharan.ch>
* feat(faster-whisper): wire version into bump-deps workflow
Assisted-by: opencode:gpt-5.5
Signed-off-by: Andreas Egli <github@kharan.ch>
---------
Signed-off-by: Andreas Egli <github@kharan.ch>
Co-authored-by: localai-org-maint-bot <bot-opensource@localaisrl.com>
The mlx, mlx-vlm, mlx-distributed and vllm-omni backends only forwarded
enable_thinking when the metadata value was "true". A "false" value never
reached apply_chat_template, so requests with thinking disabled (for
example a realtime pipeline with disable_thinking: true) still used the
chat template default. Apply the same coerce that #11715 added to sglang
and vllm.
Assisted-by: Claude:claude-opus-5
Signed-off-by: devv-shayan <shayankhanx1x@gmail.com>
* fix(whisper): honour positional listen address argument
The whisper backend parsed its gRPC listen address exclusively through
Go's flag package, while run.sh forwards launcher arguments verbatim.
A bare positional address was silently dropped by flag.Parse(), so the
server always bound the default localhost:50051 instead of the port its
caller allocated — LocalAI then failed to reach it with a misleading
'error reading from server: EOF'.
Fall back to the first positional argument when no explicit -addr value
was given, keeping the default for no-argument launches.
Fixes#11623
Assisted-by: ox-alpha:ox-alpha [go test]
Signed-off-by: Som Samantray <som.samantray@gmail.com>
* fix(whisper): track explicit -addr via flag.Visit and adopt Ginkgo test style
Review follow-up:
- Detect an explicitly set -addr with flag.FlagSet.Visit instead of
comparing against the default sentinel, so '-addr localhost:50051'
plus a positional argument keeps the flag value.
- Treat an explicitly empty -addr as unset rather than binding the
empty address (OS-chosen port on all interfaces).
- Rewrite addr_test.go as Ginkgo v2 specs per .agents/coding-style.md;
stdlib t.Run/t.Errorf are forbidden by .golangci.yml forbidigo.
Assisted-by: ox-alpha:ox-alpha [go test]
Signed-off-by: Som Samantray <som.samantray@gmail.com>
---------
Signed-off-by: Som Samantray <som.samantray@gmail.com>
Backend processes shared the host temporary directory, so crashes could leave request images and audio behind until the filesystem filled. Give each process a locked LocalAI-owned runtime, remove scratch on exit, and sweep only marked abandoned runtimes at the next start.
Also close known request error-path leaks in the Python media backends, CrispASR, LongCat Video, and stable-diffusion.cpp.
Assisted-by: Codex:gpt-5
Co-authored-by: Ettore Di Giacinto <mudler@localai.io>
RF-DETR and Locate Anything wrote each decoded request image to the OS
temporary directory. A full temporary filesystem then disabled detection,
even though both native libraries already accept encoded image buffers.
Pass decoded images directly to the native buffer APIs. This removes the
request-time disk dependency and prevents crash-orphaned image files.
Assisted-by: Codex:gpt-5
Co-authored-by: Ettore Di Giacinto <mudler@localai.io>
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>
