mirror of
https://github.com/mudler/LocalAI.git
synced 2026-08-04 12:22:22 -04:00
21ecc799e5
tests-qwen3-tts-cpp has been failing on master since 2026-07-31. The suite
loads every component fine and then stops: TTS() never returns from the
native call, so a job that takes ~5 minutes runs into the 20 minute Go test
timeout instead.
goroutine 74 [syscall, 19 minutes]:
github.com/ebitengine/purego.RegisterFunc.func4
qwen3-tts-cpp.(*Qwen3TtsCpp).TTS goqwen3ttscpp.go:154
qwen3-tts-cpp.init.func2.4 e2e_test.go:90
Not a flake: reproduced on master and again on an explicit re-run.
Bisected across this cycle's eight qwentts.cpp bumps by their own check:
10832, 10850, 10902, 10964, 11006, 11039 and 11127 all pass in ~5 minutes;
11241 (abab6b3) fails at 1h58m. That PR was merged with this check already
red, which is how the hang reached master.
35ebe537..abab6b3 is three upstream commits, and the only functional one is
26dd8adb, "predictor: unroll the frame into one cgraph and sample in standard
ops", which is consistent with a generation loop that never reaches its stop
condition.
Hold the pin at the last known-good commit. The bump entry is commented out
rather than left in place, because it tracks upstream master and would put
the hang straight back on the next nightly run. Both spots carry a pointer to
the other so the hold is discoverable, and restoring it is uncommenting four
lines once upstream is fixed.
Assisted-by: Claude Code:claude-opus-5 [Read] [Edit] [Bash]
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
Co-authored-by: Ettore Di Giacinto <mudler@localai.io>
243 lines
10 KiB
YAML
243 lines
10 KiB
YAML
name: Bump Backend dependencies
|
|
on:
|
|
schedule:
|
|
- cron: 0 20 * * *
|
|
workflow_dispatch:
|
|
jobs:
|
|
bump-backends:
|
|
if: github.repository == 'mudler/LocalAI'
|
|
strategy:
|
|
fail-fast: false
|
|
matrix:
|
|
include:
|
|
- repository: "ggml-org/llama.cpp"
|
|
variable: "LLAMA_VERSION"
|
|
branch: "master"
|
|
file: "backend/cpp/llama-cpp/Makefile"
|
|
- repository: "ikawrakow/ik_llama.cpp"
|
|
variable: "IK_LLAMA_VERSION"
|
|
branch: "main"
|
|
file: "backend/cpp/ik-llama-cpp/Makefile"
|
|
- repository: "TheTom/llama-cpp-turboquant"
|
|
variable: "TURBOQUANT_VERSION"
|
|
branch: "feature/turboquant-kv-cache"
|
|
file: "backend/cpp/turboquant/Makefile"
|
|
- repository: "PrismML-Eng/llama.cpp"
|
|
variable: "BONSAI_VERSION"
|
|
branch: "prism"
|
|
file: "backend/cpp/bonsai/Makefile"
|
|
- repository: "antirez/ds4"
|
|
variable: "DS4_VERSION"
|
|
branch: "main"
|
|
file: "backend/cpp/ds4/Makefile"
|
|
- repository: "0xShug0/audio.cpp"
|
|
variable: "AUDIO_CPP_VERSION"
|
|
branch: "main"
|
|
file: "backend/cpp/audio-cpp/Makefile"
|
|
- repository: "meituan-longcat/LongCat-Video"
|
|
variable: "LONGCAT_VIDEO_VERSION"
|
|
branch: "main"
|
|
file: "backend/python/longcat-video/Makefile"
|
|
- repository: "localai-org/privacy-filter.cpp"
|
|
variable: "PRIVACY_FILTER_VERSION"
|
|
branch: "master"
|
|
file: "backend/cpp/privacy-filter/Makefile"
|
|
- repository: "ggml-org/whisper.cpp"
|
|
variable: "WHISPER_CPP_VERSION"
|
|
branch: "master"
|
|
file: "backend/go/whisper/Makefile"
|
|
- repository: "CrispStrobe/CrispASR"
|
|
variable: "CRISPASR_VERSION"
|
|
branch: "main"
|
|
file: "backend/go/crispasr/Makefile"
|
|
- repository: "mudler/parakeet.cpp"
|
|
variable: "PARAKEET_VERSION"
|
|
branch: "master"
|
|
file: "backend/go/parakeet-cpp/Makefile"
|
|
- repository: "mudler/vllm.cpp"
|
|
variable: "VLLM_CPP_VERSION"
|
|
branch: "main"
|
|
file: "backend/go/vllm-cpp/Makefile"
|
|
- repository: "localai-org/moss-transcribe.cpp"
|
|
variable: "MOSS_VERSION"
|
|
branch: "master"
|
|
file: "backend/go/moss-transcribe-cpp/Makefile"
|
|
- repository: "localai-org/ced.cpp"
|
|
variable: "CED_VERSION"
|
|
branch: "main"
|
|
file: "backend/go/ced/Makefile"
|
|
- repository: "localai-org/voice-detect.cpp"
|
|
variable: "VOICEDETECT_VERSION"
|
|
branch: "master"
|
|
file: "backend/go/voice-detect/Makefile"
|
|
- repository: "mudler/face-detect.cpp"
|
|
variable: "FACEDETECT_VERSION"
|
|
branch: "master"
|
|
file: "backend/go/face-detect/Makefile"
|
|
- repository: "mudler/depth-anything.cpp"
|
|
variable: "DEPTHANYTHING_VERSION"
|
|
branch: "master"
|
|
file: "backend/go/depth-anything-cpp/Makefile"
|
|
- repository: "leejet/stable-diffusion.cpp"
|
|
variable: "STABLEDIFFUSION_GGML_VERSION"
|
|
branch: "master"
|
|
file: "backend/go/stablediffusion-ggml/Makefile"
|
|
- repository: "localai-org/trellis2cpp"
|
|
variable: "TRELLIS2CPP_VERSION"
|
|
branch: "pbr-textures"
|
|
file: "backend/go/trellis2cpp/Makefile"
|
|
- repository: "mudler/go-piper"
|
|
variable: "PIPER_VERSION"
|
|
branch: "master"
|
|
file: "backend/go/piper/Makefile"
|
|
- repository: "antirez/voxtral.c"
|
|
variable: "VOXTRAL_VERSION"
|
|
branch: "main"
|
|
file: "backend/go/voxtral/Makefile"
|
|
- repository: "ace-step/acestep.cpp"
|
|
variable: "ACESTEP_CPP_VERSION"
|
|
branch: "master"
|
|
file: "backend/go/acestep-cpp/Makefile"
|
|
- repository: "PABannier/sam3.cpp"
|
|
variable: "SAM3_VERSION"
|
|
branch: "main"
|
|
file: "backend/go/sam3-cpp/Makefile"
|
|
- repository: "localai-org/rf-detr.cpp"
|
|
variable: "RFDETR_VERSION"
|
|
branch: "main"
|
|
file: "backend/go/rfdetr-cpp/Makefile"
|
|
- repository: "mudler/locate-anything.cpp"
|
|
variable: "LOCATEANYTHING_VERSION"
|
|
branch: "master"
|
|
file: "backend/go/locate-anything-cpp/Makefile"
|
|
# qwentts.cpp is held, not tracked: upstream master hangs in synthesis
|
|
# (see the comment on QWEN3TTS_CPP_VERSION in the backend Makefile).
|
|
# Leaving it here would re-bump the pin back onto the hang every night.
|
|
# Restore this entry once the upstream fix lands.
|
|
# - repository: "ServeurpersoCom/qwentts.cpp"
|
|
# variable: "QWEN3TTS_CPP_VERSION"
|
|
# branch: "master"
|
|
# file: "backend/go/qwen3-tts-cpp/Makefile"
|
|
- repository: "ServeurpersoCom/omnivoice.cpp"
|
|
variable: "OMNIVOICE_VERSION"
|
|
branch: "master"
|
|
file: "backend/go/omnivoice-cpp/Makefile"
|
|
- repository: "localai-org/vibevoice.cpp"
|
|
variable: "VIBEVOICE_CPP_VERSION"
|
|
branch: "master"
|
|
file: "backend/go/vibevoice-cpp/Makefile"
|
|
- repository: "mudler/magpie-tts.cpp"
|
|
variable: "MAGPIETTS_CPP_VERSION"
|
|
branch: "main"
|
|
file: "backend/go/magpie-tts-cpp/Makefile"
|
|
runs-on: ubuntu-latest
|
|
steps:
|
|
- uses: actions/checkout@v7
|
|
- name: Bump dependencies 🔧
|
|
id: bump
|
|
env:
|
|
# This job fans out to ~25 parallel matrix entries, all querying
|
|
# api.github.com from runner IPs that share the 60/hour anonymous
|
|
# rate limit. Authenticating raises it to 1000/hour, which is what
|
|
# kept a random handful of these red every night.
|
|
GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
|
|
run: |
|
|
bash .github/bump_deps.sh ${{ matrix.repository }} ${{ matrix.branch }} ${{ matrix.variable }} ${{ matrix.file }}
|
|
{
|
|
echo 'message<<EOF'
|
|
cat "${{ matrix.variable }}_message.txt"
|
|
echo EOF
|
|
} >> "$GITHUB_OUTPUT"
|
|
{
|
|
echo 'commit<<EOF'
|
|
cat "${{ matrix.variable }}_commit.txt"
|
|
echo EOF
|
|
} >> "$GITHUB_OUTPUT"
|
|
rm -rfv ${{ matrix.variable }}_message.txt
|
|
rm -rfv ${{ matrix.variable }}_commit.txt
|
|
- name: Create Pull Request
|
|
uses: peter-evans/create-pull-request@v8
|
|
with:
|
|
token: ${{ secrets.UPDATE_BOT_TOKEN }}
|
|
push-to-fork: ci-forks/LocalAI
|
|
commit-message: ':arrow_up: Update ${{ matrix.repository }}'
|
|
title: 'chore: :arrow_up: Update ${{ matrix.repository }} to `${{ steps.bump.outputs.commit }}`'
|
|
branch: "update/${{ matrix.variable }}"
|
|
body: ${{ steps.bump.outputs.message }}
|
|
signoff: true
|
|
|
|
bump-vllm-wheel:
|
|
# vLLM's cu130 wheel comes from a per-tag index URL (no /latest/ alias),
|
|
# so the cublas13 requirements file pins both a URL segment and a version
|
|
# constraint. bump_deps.sh handles git-sha-in-Makefile only — this job
|
|
# rewrites both values atomically when a new vLLM stable tag ships.
|
|
if: github.repository == 'mudler/LocalAI'
|
|
runs-on: ubuntu-latest
|
|
steps:
|
|
- uses: actions/checkout@v7
|
|
- name: Bump vLLM cu130 wheel pin 🔧
|
|
id: bump
|
|
env:
|
|
GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
|
|
run: |
|
|
bash .github/bump_vllm_wheel.sh vllm-project/vllm backend/python/vllm/requirements-cublas13-after.txt VLLM_VERSION
|
|
{
|
|
echo 'message<<EOF'
|
|
cat "VLLM_VERSION_message.txt"
|
|
echo EOF
|
|
} >> "$GITHUB_OUTPUT"
|
|
{
|
|
echo 'commit<<EOF'
|
|
cat "VLLM_VERSION_commit.txt"
|
|
echo EOF
|
|
} >> "$GITHUB_OUTPUT"
|
|
rm -rfv VLLM_VERSION_message.txt VLLM_VERSION_commit.txt
|
|
- name: Create Pull Request
|
|
uses: peter-evans/create-pull-request@v8
|
|
with:
|
|
token: ${{ secrets.UPDATE_BOT_TOKEN }}
|
|
push-to-fork: ci-forks/LocalAI
|
|
commit-message: ':arrow_up: Update vllm-project/vllm cu130 wheel'
|
|
title: 'chore: :arrow_up: Update vllm-project/vllm cu130 wheel to `${{ steps.bump.outputs.commit }}`'
|
|
branch: "update/VLLM_VERSION"
|
|
body: ${{ steps.bump.outputs.message }}
|
|
signoff: true
|
|
|
|
bump-vllm-metal:
|
|
# The darwin (Apple Silicon) vLLM build installs vllm-metal, which is locked
|
|
# to a specific vLLM source release. install.sh pins both VLLM_METAL_VERSION
|
|
# (the wheel release) and VLLM_VERSION (the vLLM it builds against); this job
|
|
# tracks vllm-project/vllm-metal and rewrites both atomically. Separate from
|
|
# bump-vllm-wheel because darwin follows vllm-metal, not vllm/vllm latest.
|
|
if: github.repository == 'mudler/LocalAI'
|
|
runs-on: ubuntu-latest
|
|
steps:
|
|
- uses: actions/checkout@v7
|
|
- name: Bump vllm-metal pin 🔧
|
|
id: bump
|
|
env:
|
|
GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
|
|
run: |
|
|
bash .github/bump_vllm_metal.sh vllm-project/vllm-metal backend/python/vllm/install.sh VLLM_METAL_VERSION
|
|
{
|
|
echo 'message<<EOF'
|
|
cat "VLLM_METAL_VERSION_message.txt"
|
|
echo EOF
|
|
} >> "$GITHUB_OUTPUT"
|
|
{
|
|
echo 'commit<<EOF'
|
|
cat "VLLM_METAL_VERSION_commit.txt"
|
|
echo EOF
|
|
} >> "$GITHUB_OUTPUT"
|
|
rm -rfv VLLM_METAL_VERSION_message.txt VLLM_METAL_VERSION_commit.txt
|
|
- name: Create Pull Request
|
|
uses: peter-evans/create-pull-request@v8
|
|
with:
|
|
token: ${{ secrets.UPDATE_BOT_TOKEN }}
|
|
push-to-fork: ci-forks/LocalAI
|
|
commit-message: ':arrow_up: Update vllm-project/vllm-metal (darwin)'
|
|
title: 'chore: :arrow_up: Update vllm-metal (darwin) to `${{ steps.bump.outputs.commit }}`'
|
|
branch: "update/VLLM_METAL_VERSION"
|
|
body: ${{ steps.bump.outputs.message }}
|
|
signoff: true
|