[TEST] Add Qwen3-32b-w8a8 acc/perf A2/A3 test (#3541)
### What this PR does / why we need it? This PR Qwen3-32b-w8a8 acc/perf 8 cases on A2 and A3, we need test them daily. ### Does this PR introduce _any_ user-facing change? No ### How was this patch tested? by running the test - vLLM version: v0.11.0rc3 - vLLM main: https://github.com/vllm-project/vllm/commit/v0.11.0 --------- Signed-off-by: jiangyunfan1 <jiangyunfan1@h-partners.com> Signed-off-by: wangli <wangli858794774@gmail.com> Signed-off-by: Yikun Jiang <yikunkero@gmail.com> Signed-off-by: root <root@hostname-2pbfv.foreman.pxe> Co-authored-by: wangli <wangli858794774@gmail.com> Co-authored-by: Yikun Jiang <yikunkero@gmail.com>
This commit is contained in:
1
.github/workflows/_e2e_nightly.yaml
vendored
1
.github/workflows/_e2e_nightly.yaml
vendored
@@ -109,6 +109,7 @@ jobs:
|
||||
env:
|
||||
VLLM_WORKER_MULTIPROC_METHOD: spawn
|
||||
VLLM_USE_MODELSCOPE: True
|
||||
VLLM_CI_RUNNER: ${{ inputs.runner }}
|
||||
run: |
|
||||
# TODO: enable more tests
|
||||
pytest -sv ${{ inputs.tests }}
|
||||
|
||||
Reference in New Issue
Block a user