Skip to content

Commit a91e76c

Browse files
authored
[CI] clean up ci (#4452)
1. Run 4-card test only when single and 2-card test passed 2. rename file to make it more clear 3. remove useless pd workflow, it has been managed by nightly test already. - vLLM version: v0.11.2 - vLLM main: https://github.com/vllm-project/vllm/commit/v0.11.2 Signed-off-by: wangxiyuan <wangxiyuan1007@gmail.com>
1 parent bc69d7c commit a91e76c

File tree

4 files changed

+3
-116
lines changed

4 files changed

+3
-116
lines changed

.github/workflows/_e2e_test.yaml

Lines changed: 3 additions & 4 deletions
Original file line numberDiff line numberDiff line change
@@ -111,9 +111,6 @@ jobs:
111111
# Fix me: test_eagle_correctness OOM error
112112
pytest -sv tests/e2e/singlecard/spec_decode_v1/test_v1_spec_decode.py
113113
114-
# TODO: Move ops test to nightly test
115-
#pytest -sv tests/e2e/singlecard/ops/
116-
117114
e2e-2-cards:
118115
name: multicard-2
119116
runs-on: ${{ inputs.runner }}-2
@@ -210,6 +207,8 @@ jobs:
210207
211208
e2e-4-cards:
212209
name: multicard-4
210+
needs: [e2e, e2e-2-cards]
211+
if: ${{ needs.e2e.result == 'success' && needs.e2e-2-cards.result == 'success' && inputs.type == 'full' }}
213212
runs-on: linux-aarch64-a3-4
214213
container:
215214
image: m.daocloud.io/quay.io/ascend/cann:8.3.rc1-a3-ubuntu22.04-py3.11
@@ -289,4 +288,4 @@ jobs:
289288
VLLM_USE_MODELSCOPE: True
290289
run: |
291290
. /usr/local/Ascend/8.3.RC1/bisheng_toolkit/set_env.sh
292-
pytest -sv tests/e2e/multicard/test_qwen3_next.py
291+
pytest -sv tests/e2e/multicard/test_qwen3_next.py

.github/workflows/vllm_ascend_test_pd.yaml

Lines changed: 0 additions & 112 deletions
This file was deleted.

0 commit comments

Comments
 (0)