LocalAI/.github/workflows
Ettore Di Giacinto 24505e57f5
feat(backends): add CUDA 13 + L4T arm64 CUDA 13 variants for vllm/vllm-omni/sglang (#9553)
* 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>
2026-04-25 12:26:29 +02:00
..
disabled chore(ci): disable CI actions 2026-03-02 14:48:00 +01:00
backend.yml feat(backends): add CUDA 13 + L4T arm64 CUDA 13 variants for vllm/vllm-omni/sglang (#9553) 2026-04-25 12:26:29 +02:00
backend_build.yml feat: voice recognition (#9500) 2026-04-23 12:07:14 +02:00
backend_build_darwin.yml chore(deps): bump docker/metadata-action from 5 to 6 (#8917) 2026-03-09 22:27:02 +01:00
backend_pr.yml Change runner from macOS-14 to macos-latest 2025-12-13 10:11:27 +01:00
build-test.yaml chore(deps): bump actions/upload-artifact from 6 to 7 (#8730) 2026-03-02 21:43:39 +01:00
bump-inference-defaults.yml chore(deps): bump peter-evans/create-pull-request from 7 to 8 (#9114) 2026-03-24 08:50:50 +01:00
bump_deps.yaml feat(backend): add turboquant llama.cpp-fork backend (#9355) 2026-04-15 01:25:04 +02:00
bump_docs.yaml fix(api)!: Stop model prior to deletion (#8422) 2026-02-06 09:22:10 +01:00
checksum_checker.yaml fix(api)!: Stop model prior to deletion (#8422) 2026-02-06 09:22:10 +01:00
deploy-explorer.yaml fix(api)!: Stop model prior to deletion (#8422) 2026-02-06 09:22:10 +01:00
gallery-agent.yaml fix(gallery-agent): process blacklist command on recently-closed PRs (#9473) 2026-04-21 16:29:13 +02:00
generate_grpc_cache.yaml chore(deps): bump docker/build-push-action from 6 to 7 (#8919) 2026-03-09 22:29:51 +01:00
generate_intel_image.yaml [intel GPU support] Use latest oneapi-basekit image for Intel images to support b70 (#9543) 2026-04-24 18:29:10 +02:00
gh-pages.yml chore(deps): bump actions/upload-pages-artifact from 4 to 5 (#9337) 2026-04-13 21:53:47 +02:00
image-pr.yml feat(rocm): bump to 7.x (#9323) 2026-04-12 08:51:30 +02:00
image.yml feat(rocm): bump to 7.x (#9323) 2026-04-12 08:51:30 +02:00
image_build.yml chore: drop AIO images (#9004) 2026-03-14 17:49:36 +01:00
notify-releases.yaml fix(api)!: Stop model prior to deletion (#8422) 2026-02-06 09:22:10 +01:00
release.yaml chore(deps): bump softprops/action-gh-release from 2 to 3 (#9336) 2026-04-13 21:53:28 +02:00
secscan.yaml Revert "chore(deps): bump securego/gosec from 2.22.9 to 2.22.11" (#7789) 2025-12-30 09:58:13 +01:00
stalebot.yml chore(deps): bump actions/stale from 10.1.1 to 10.2.0 (#8633) 2026-02-23 23:27:20 +01:00
test-extra.yml feat: Add Sherpa ONNX backend for ASR and TTS (#8523) 2026-04-24 14:40:06 +02:00
test.yml feat: Add Sherpa ONNX backend for ASR and TTS (#8523) 2026-04-24 14:40:06 +02:00
tests-e2e.yml feat(realtime): WebRTC support (#8790) 2026-03-13 21:37:15 +01:00
tests-ui-e2e.yml chore(deps): bump actions/upload-artifact from 4 to 7 (#9030) 2026-03-17 11:42:49 +01:00
update_swagger.yaml fix(api)!: Stop model prior to deletion (#8422) 2026-02-06 09:22:10 +01:00
yaml-check.yml chore(backend gallery): add description for remaining backends (#5679) 2025-06-17 22:21:44 +02:00