[CI/UT] fix spec ut in vllm-ascend main and vllm main (#759)

### What this PR does / why we need it?
#### 1. fix spec ut in vllm-ascend main and vllm main
As https://github.com/vllm-project/vllm-ascend/pull/694 and
https://github.com/vllm-project/vllm-ascend/pull/749 verify, Now,
vllm-ascend main and vllm 0.8.5, spec UT is happy, but vllm-ascend main
and vllm main, CI is fail.

I found the reason is a triton bug
https://github.com/triton-lang/triton/issues/2266, but i I didn't figure
it out that why the bug did not effect vllm-ascend main and vllm 0.8.5,
maybe the usage of triton have changed when vllm 0.8.5 to latest main

As the bug describe, I changed the minimum block_size in UT from 8 to
16, and the modification is verified locally to be effective.

#### 2. modify some case skip form.
I modified some commented out cases to skipif form, which is more
standardized.

### Does this PR introduce _any_ user-facing change?
None

### How was this patch tested?
CI

Signed-off-by: mengwei805 <mengwei25@huawei.com>
This commit is contained in:
wemaster
2025-05-10 09:45:56 +08:00
committed by GitHub
parent 58d2f85c4a
commit 19c8e134e4
5 changed files with 265 additions and 273 deletions

View File

@@ -153,8 +153,7 @@ jobs:
- "vllm_ascend/patch/worker/patch_common/patch_multi_step_worker.py"
- name: Run vllm-project/vllm-ascend Speculative Decode test
# speculative decode seems will cause oom issue, only disable it now on ci test with vLLM main
if: matrix.vllm_verison == 'v0.8.5.post1' && steps.filter_spec_decode.outputs.speculative_tests_changed == 'true' || github.event_name == 'schedule'
if: steps.filter_spec_decode.outputs.speculative_tests_changed == 'true' || github.event_name == 'schedule'
run: |
if [[ "${{ matrix.os }}" == "linux-arm64-npu-1" ]]; then
pytest -sv tests/singlecard/spec_decode/e2e/test_mtp_correctness.py # it needs a clean process