[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 ${{ inputs.tests }}
|
||||
|
||||
21
.github/workflows/vllm_ascend_test_nightly.yaml
vendored
21
.github/workflows/vllm_ascend_test_nightly.yaml
vendored
@@ -41,7 +41,7 @@ defaults:
|
||||
# and ignore the lint / 1 card / 4 cards test type
|
||||
concurrency:
|
||||
group: ascend-nightly-${{ github.ref }}
|
||||
cancel-in-progress: true
|
||||
#cancel-in-progress: true
|
||||
|
||||
jobs:
|
||||
qwen3-32b:
|
||||
@@ -56,3 +56,22 @@ jobs:
|
||||
vllm: v0.11.0
|
||||
runner: ${{ matrix.os }}
|
||||
tests: tests/e2e/nightly/models/test_qwen3_32b.py
|
||||
qwen3-32b-in8-a3:
|
||||
strategy:
|
||||
matrix:
|
||||
os: [linux-aarch64-a3-4]
|
||||
uses: ./.github/workflows/_e2e_nightly.yaml
|
||||
with:
|
||||
vllm: v0.11.0
|
||||
runner: ${{ matrix.os }}
|
||||
image: swr.cn-southwest-2.myhuaweicloud.com/base_image/ascend-ci/cann:8.2.rc1-a3-ubuntu22.04-py3.11
|
||||
tests: tests/e2e/nightly/models/test_qwen3_32b_int8.py
|
||||
qwen3-32b-in8-a2:
|
||||
strategy:
|
||||
matrix:
|
||||
os: [linux-aarch64-a2-4]
|
||||
uses: ./.github/workflows/_e2e_nightly.yaml
|
||||
with:
|
||||
vllm: v0.11.0
|
||||
runner: ${{ matrix.os }}
|
||||
tests: tests/e2e/nightly/models/test_qwen3_32b_int8.py
|
||||
|
||||
Reference in New Issue
Block a user