[9/n] decouple quantization impl from vllm dependency - adjust ci (#12753)

This commit is contained in:
Peng Zhang
2025-11-11 06:55:19 +08:00
committed by GitHub
parent 0493775b06
commit 012bfc4fdc
4 changed files with 13 additions and 13 deletions

View File

@@ -1,4 +1,4 @@
name: VLLM Dependency Test
name: Quantization Test
on:
push:
@@ -8,7 +8,7 @@ on:
- "!python/sglang/multimodal_gen/**"
- "scripts/ci/**"
- "test/**"
- ".github/workflows/vllm-dependency-test.yml"
- ".github/workflows/quantization-test.yml"
pull_request:
branches: [ main ]
paths:
@@ -16,16 +16,16 @@ on:
- "!python/sglang/multimodal_gen/**"
- "scripts/ci/**"
- "test/**"
- ".github/workflows/vllm-dependency-test.yml"
- ".github/workflows/quantization-test.yml"
types: [synchronize, labeled]
workflow_dispatch:
concurrency:
group: vllm-dependency-test-${{ github.ref }}
group: quantization-test-${{ github.ref }}
cancel-in-progress: true
jobs:
vllm-dependency-test:
quantization-test:
if: github.event_name != 'pull_request' || contains(github.event.pull_request.labels.*.name, 'run-ci')
runs-on: 1-gpu-runner
steps:
@@ -37,8 +37,8 @@ jobs:
bash scripts/ci/ci_install_dependency.sh
pip install "bitsandbytes>=0.44.0"
- name: Run vLLM dependency tests
- name: Run Quantization tests
timeout-minutes: 30
run: |
cd test/srt
python3 run_suite.py --suite vllm_dependency_test
python3 run_suite.py --suite quantization_test