* feat(vllm): macOS/Metal support via vllm-metal (MLX)
Add an additive Apple-Silicon path to the existing vllm Python backend so
vLLM runs on macOS via vllm-metal (github.com/vllm-project/vllm-metal).
Spike outcome (proven on a real M4 / macOS 26.5, Qwen3-0.6B):
- vllm-metal registers through vLLM's platform-plugin entry point
(metal -> vllm_metal:register); MetalPlatform activates and runs on the
GPU through MLX.
- LocalAI's backend.py is UNCHANGED: AsyncEngineArgs(...) ->
AsyncLLMEngine.from_engine_args transparently resolves to vLLM 0.23's v1
AsyncLLM MLX engine, and async generate produced correct output.
- backend.py is NOT touched: its only empty_cache() call is CUDA-only
(guarded by torch.cuda.is_available()), so the benign shutdown-only
"Allocator for mps is not a DeviceAllocator" noise comes from vLLM's
internal EngineCore teardown, not from our code.
Changes (all gated behind a darwin condition; Linux/CUDA/ROCm/Intel paths
are byte-for-byte unchanged):
- install.sh: darwin branch forces PYTHON_VERSION=3.12 (vllm-metal
requirement), creates/activates LocalAI's managed venv via ensureVenv,
then reproduces vllm-metal's installer INTO that venv (build vLLM 0.23.0
from the release source tarball against requirements/cpu.txt, then install
the prebuilt vllm-metal wheel from its latest GitHub release), and runs
runProtogen. installRequirements is skipped on darwin.
- backend-matrix.yml: add a vllm includeDarwin entry (mps, python).
- index.yaml: add metal capability + concrete metal-vllm /
metal-vllm-development child entries mirroring the metal-kitten-tts
template.
Version coupling: vllm-metal pins vLLM 0.23.0, equal to LocalAI's current
vllm pin. Bumping vllm must be coordinated with a supporting vllm-metal
release; documented in install.sh and requirements-cublas13-after.txt.
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
Assisted-by: Claude:opus-4.8 [Claude Code]
* chore(vllm): track the darwin vllm-metal pin via the autobumper
The Apple Silicon build pinned vLLM 0.23.0 as a hidden string in install.sh
while floating the vllm-metal wheel on releases/latest - the two could drift
apart silently. Make both a tracked, reproducible pair (VLLM_METAL_VERSION +
VLLM_VERSION), fetch the wheel by tag, and add .github/bump_vllm_metal.sh wired
into bump_deps.yaml. It tracks vllm-project/vllm-metal (not vllm/vllm latest),
reading the coupled vLLM source version from vllm-metal's own installer, and
opens a bump PR - mirroring the existing bump_vllm_wheel.sh for the cu130 wheel.
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
Assisted-by: Claude:opus-4.8 [Claude Code]
* chore(vllm): derive the darwin vLLM version, drop the second pin
Follow-up: VLLM_VERSION was still a hardcoded string duplicating what
VLLM_METAL_VERSION already determines. Derive it at install time from
vllm-metal's own installer (vllm_v=) at the pinned tag - one source of truth,
no second value to drift. The bumper now touches only VLLM_METAL_VERSION;
the derivation is immutable per tag, so builds stay reproducible.
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
Assisted-by: Claude:opus-4.8 [Claude Code]
* fix(vllm): fetch the vllm-metal wheel without the GitHub API
The darwin build resolved the wheel URL via api.github.com, whose
unauthenticated rate limit (60/hr per IP) 403s on shared macOS runners
(observed after the 9-min vLLM source build). Construct the release-asset
download URL deterministically from the pinned tag and the cp312/arm64 wheel
name instead - no API call, no rate limit. Verified the URL resolves (200).
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
Assisted-by: Claude:opus-4.8 [Claude Code]
* fix(vllm): fail Score cleanly when the engine returns no prompt_logprobs
Audit of the Score path against vllm-metal (MLX on macOS): the engine accepts
SamplingParams(prompt_logprobs=1) but returns an all-None prompt_logprobs list
rather than computing it, so scoring is not supported there. The old guard
treated the truthy [None] list as valid and silently scored every candidate as
0. Detect the all-None case and return UNIMPLEMENTED instead. No-op on
Linux/CUDA, which populate real entries.
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
Assisted-by: Claude:opus-4.8 [Claude Code]
---------
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
Co-authored-by: Ettore Di Giacinto <mudler@localai.io>
* feat(vllm): expose AsyncEngineArgs via generic engine_args YAML map
LocalAI's vLLM backend wraps a small typed subset of vLLM's
AsyncEngineArgs (quantization, tensor_parallel_size, dtype, etc.).
Anything outside that subset -- pipeline/data/expert parallelism,
speculative_config, kv_transfer_config, all2all_backend, prefix
caching, chunked prefill, etc. -- requires a new protobuf field, a
Go struct field, an options.go line, and a backend.py mapping per
feature. That cadence is the bottleneck on shipping vLLM's
production feature set.
Add a generic `engine_args:` map on the model YAML that is
JSON-serialised into a new ModelOptions.EngineArgs proto field and
applied verbatim to AsyncEngineArgs at LoadModel time. Validation
is done by the Python backend via dataclasses.fields(); unknown
keys fail with the closest valid name as a hint.
dataclasses.replace() is used so vLLM's __post_init__ re-runs and
auto-converts dict values into nested config dataclasses
(CompilationConfig, AttentionConfig, ...). speculative_config and
kv_transfer_config flow through as dicts; vLLM converts them at
engine init.
Operators can now write:
engine_args:
data_parallel_size: 8
enable_expert_parallel: true
all2all_backend: deepep_low_latency
speculative_config:
method: deepseek_mtp
num_speculative_tokens: 3
kv_cache_dtype: fp8
without further proto/Go/Python plumbing per field.
Production defaults seeded by hooks_vllm.go: enable_prefix_caching
and enable_chunked_prefill default to true unless explicitly set.
Existing typed YAML fields (gpu_memory_utilization,
tensor_parallel_size, etc.) remain for back-compat; engine_args
overrides them when both are set.
Assisted-by: Claude:claude-opus-4-7 [Claude Code]
Signed-off-by: Richard Palethorpe <io@richiejp.com>
* chore(vllm): pin cublas13 to vLLM 0.20.0 cu130 wheel
vLLM's PyPI wheel is built against CUDA 12 (libcudart.so.12) and won't
load on a cu130 host. Switch the cublas13 build to vLLM's per-tag cu130
simple-index (https://wheels.vllm.ai/0.20.0/cu130/) and pin
vllm==0.20.0. The cu130-flavoured wheel ships libcudart.so.13 and
includes the DFlash speculative-decoding method that landed in 0.20.0.
cublas13 install gets --index-strategy=unsafe-best-match so uv consults
both the cu130 index and PyPI when resolving — PyPI also publishes
vllm==0.20.0, but with cu12 binaries that error at import time.
Verified: Qwen3.5-4B + z-lab/Qwen3.5-4B-DFlash loads and serves chat
completions on RTX 5070 Ti (sm_120, cu130).
Assisted-by: Claude:claude-opus-4-7 [Claude Code]
Signed-off-by: Richard Palethorpe <io@richiejp.com>
* ci(vllm): bot job to bump cublas13 vLLM wheel pin
vLLM's cu130 wheel index URL is itself version-locked
(wheels.vllm.ai/<TAG>/cu130/, no /latest/ alias upstream), so a vLLM
bump means rewriting two values atomically — the URL segment and the
version constraint. bump_deps.sh handles git-sha-in-Makefile only;
add a sibling bump_vllm_wheel.sh and a matching workflow job that
mirrors the existing matrix's PR-creation pattern.
The bumper queries /releases/latest (which excludes prereleases),
strips the leading 'v', and seds both lines unconditionally. When the
file is already on the latest tag the rewrite is a no-op and
peter-evans/create-pull-request opens no PR.
Assisted-by: Claude:claude-opus-4-7 [Claude Code]
Signed-off-by: Richard Palethorpe <io@richiejp.com>
* docs(vllm): document engine_args and speculative decoding
The new engine_args: map plumbs arbitrary AsyncEngineArgs through to
vLLM, but the public docs only covered the basic typed fields. Add a
short subsection in the vLLM section explaining the typed/generic
split and showing a worked DFlash speculative-decoding config, with
pointers to vLLM's SpeculativeConfig reference and z-lab's drafter
collection.
Assisted-by: Claude:claude-opus-4-7 [Claude Code]
Signed-off-by: Richard Palethorpe <io@richiejp.com>
---------
Signed-off-by: Richard Palethorpe <io@richiejp.com>
Co-authored-by: Ettore Di Giacinto <mudler@users.noreply.github.com>
* feat(backends): add CUDA 13 + L4T arm64 CUDA 13 variants for vllm/vllm-omni/sglang
Adds new build profiles mirroring the diffusers/ace-step pattern so vLLM
serving (and SGLang on arm64) can be deployed on CUDA 13 hosts and
JetPack 7 boards:
- vllm: cublas13 (PyPI cu130 channel) + l4t13 (jetson-ai-lab SBSA cu130
prebuilt vllm + flash-attn).
- vllm-omni: cublas13 + l4t13. Floats vllm version on cu13 since vllm
0.19+ ships cu130 wheels by default and vllm-omni tracks vllm master;
cu12 path keeps the 0.14.0 pin to avoid disturbing existing images.
- sglang: l4t13 arm64 only — uses the prebuilt sglang wheel from the
jetson-ai-lab SBSA cu130 index, so no source build is needed.
Cublas13 sglang on x86_64 is intentionally deferred.
CI matrix gains five new images (-gpu-nvidia-cuda-13-vllm{,-omni},
-nvidia-l4t-cuda-13-arm64-{vllm,vllm-omni,sglang}); backend/index.yaml
gains the matching capability keys (nvidia-cuda-13, nvidia-l4t-cuda-13)
and latest/development merge entries.
Assisted-by: Claude:claude-opus-4-7 [Read] [Edit] [Write] [Bash]
* fix(backends): use unsafe-best-match index strategy on l4t13 builds
The jetson-ai-lab SBSA cu130 index lists transitive deps (decord, etc.)
at limited versions / older Python ABIs. uv defaults to the first index
that contains a package and refuses to fall through to PyPI, so sglang
l4t13 build fails resolving decord. Mirror the existing cpu sglang
profile by setting --index-strategy=unsafe-best-match on l4t13 across
the three backends, and apply it to the explicit vllm install line in
vllm-omni's install.sh (which doesn't honor EXTRA_PIP_INSTALL_FLAGS).
Assisted-by: Claude:claude-opus-4-7 [Read] [Edit] [Bash]
* fix(sglang): drop [all] extras on l4t13, floor version at 0.5.0
The [all] extra brings in outlines→decord, and decord has no aarch64
cp312 wheel on PyPI nor the jetson-ai-lab index (only legacy cp35-cp37
tags). With unsafe-best-match enabled, uv backtracked through sglang
versions trying to satisfy decord and silently landed on
sglang==0.1.16, an ancient version with an entirely different dep
tree (cloudpickle/outlines 0.0.44, etc.).
Drop [all] so decord is no longer required, and floor sglang at 0.5.0
to prevent any future resolver misfire from degrading the version
again.
Assisted-by: Claude:claude-opus-4-7 [Read] [Edit] [Bash]
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
---------
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
