Translate modern speculative fields to the pinned fork API, disable unsupported score and checkpoint features, and cover the compatibility transform with an idempotent regression test.
Assisted-by: Codex:gpt-5 [Codex]
The buun build copies the stock llama.cpp backend directory, including patches that target upstream. Remove that copied patch directory before invoking the shared build so only the explicit buun compatibility series is applied to the fork.
Assisted-by: Codex:gpt-5 [systematic-debugging]
The shared gRPC wrapper stores p_split under the draft sub-structure. Match that exact source spelling so the fork-specific patch stage reaches the build on every architecture.
Assisted-by: Codex:gpt-5 [Codex]
Two more hipblas-only build failures in buun's fattn.cu, fixed under the
same patches/ infrastructure:
1. cudaMemcpyToSymbol / cudaMemcpyFromSymbol — buun's Q² calibration +
TCQ codebook upload paths call the symbol variants of cudaMemcpy.
ggml/src/ggml-cuda/vendors/hip.h aliases every other cudaMemcpy*
name (cudaMemcpy, cudaMemcpyAsync, cudaMemcpy2DAsync, …) but the
symbol pair was never added. 15+ "use of undeclared identifier"
errors across fattn.cu lines 40, 54, 74-76, 94, 100-101, 371, 883,
905, 954, 976, 1449, 1463. Add the two missing aliases alongside
the existing memcpy block.
2. __shfl_xor_sync fwht128 calls — same 3-arg omission pattern as the
earlier argmax top-K fix. Lines 512 (ggml_cuda_fwht128 intra-warp
butterfly) and 536 (fwht128_store_half neighbor fetch) drop the
width argument that hip.h:33 requires. Add WARP_SIZE.
Assisted-by: Claude:claude-opus-4-7
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
Two call sites in ggml/src/ggml-cuda/argmax.cu (the top-K intra-warp
merge added by buun) use the 3-arg CUDA form __shfl_xor_sync(mask, var,
laneMask), omitting the optional width parameter. The hipification shim
at ggml/src/ggml-cuda/vendors/hip.h:33 is a function-like macro that
requires all four arguments, so hipcc fails with:
argmax.cu:265: too few arguments provided to function-like macro
invocation
note: macro '__shfl_xor_sync' defined here:
#define __shfl_xor_sync(mask, var, laneMask, width) \
__shfl_xor(var, laneMask, width)
Every other call in the same file already passes WARP_SIZE explicitly;
aligning these two with that convention fixes the hipblas build without
changing CUDA codegen (warpSize is the CUDA default).
Assisted-by: Claude:claude-opus-4-7
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
Buun's Q² calibration path in ggml/src/ggml-cuda/fattn.cu calls
atomicAdd with a double* destination. Native double atomicAdd is only
available on CUDA compute capability 6.0 and later — LocalAI's CUDA 12
Docker image builds for the full published arch range (which includes
sm_50/sm_52), so nvcc fails with:
fattn.cu:812: error: no instance of overloaded function "atomicAdd"
matches the argument list, argument types are: (double *, double)
Add the canonical CAS-loop shim from the CUDA C Programming Guide
(B.15 Atomic Functions) guarded on __CUDA_ARCH__ < 600. On sm_60+ the
guard is false and nvcc picks up the native intrinsic as before.
Patch file lives under backend/cpp/buun-llama-cpp/patches/ and is
applied to the cloned fork tree by apply-patches.sh (the infrastructure
already put in place for exactly this class of backport).
Assisted-by: Claude:claude-opus-4-7
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
Previous substitution kept the call as 5 args, but buun predates the
upstream refactor that also *added* the logit_bias_eog parameter to
params_from_json_cmpl — buun's signature is still the 4-arg form
(const llama_vocab*, const common_params&, int, const json&)
and it still derives logit_bias_eog internally from the common_params.
Replace the substitution with a line-delete. Guard matches both the
original call (ctx_server.get_meta().logit_bias_eog) and the previously
substituted form (params_base.sampling.logit_bias_eog) so the script
stays safe across re-runs and whatever state the tree was left in.
Assisted-by: Claude:Opus-4.7 [Read] [Edit] [Bash]
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
LocalAI's shared grpc-server.cpp reaches
ctx_server.get_meta().logit_bias_eog twice (the twin params_from_json_cmpl
callsites). That accessor was added to server_context_meta upstream after
buun's 2026-04-05 fork-point, so compiling against buun errors with
'struct server_context_meta' has no member named 'logit_bias_eog'.
Rewrite the call sites — only in the buun grpc-server.cpp copy — to source
the vector from params_base.sampling.logit_bias_eog instead. That vector is
the underlying data the upstream meta accessor eventually returns (buun
still carries common_params_sampling::logit_bias_eog at common.h:280), so
the substitution yields identical behavior on both trees.
The sed is guarded by a grep for the call site, so this patch is
self-disabling once buun rebases past the upstream refactor.
Assisted-by: Claude:Opus-4.7 [Read] [Edit] [Bash] [WebFetch]
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
spiritbuun/buun-llama-cpp is a fork of TheTom/llama-cpp-turboquant that adds
two independent features on top: DFlash block-diffusion speculative decoding
(via a dedicated DFlashDraftModel GGUF arch) and two extra TCQ KV-cache
variants (turbo2_tcq, turbo3_tcq) on top of TurboQuant's turbo2/turbo3/turbo4.
Follows the turboquant thin-wrapper pattern — reuses backend/cpp/llama-cpp
grpc-server sources verbatim, patches only the build copy to extend the KV
allow-list and wire up buun-exclusive tree_budget / draft_topk options.
DraftModel is already wired end-to-end (proto field 39 → params.speculative),
so DFlash activation only needs the existing options passthrough
(spec_type:dflash) plus the drafter path in draft_model.
CacheTypeOptions now surfaces the five turbo* values so the React UI dropdown
shows them — benefits turboquant too (previously users had to type them in
YAML manually).
Assisted-by: Claude:Opus-4.7 [Read] [Edit] [Bash] [WebFetch]
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
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>
