Re-enable Speculative Decode test for vLLM v0.8.5 (#749)
### What this PR does / why we need it? Re-enable Speculative Decode test for vLLM v0.8.5 ### Does this PR introduce _any_ user-facing change? No ### How was this patch tested? CI passed Signed-off-by: Yikun Jiang <yikunkero@gmail.com>
This commit is contained in:
17
.github/workflows/vllm_ascend_test.yaml
vendored
17
.github/workflows/vllm_ascend_test.yaml
vendored
@@ -136,12 +136,23 @@ jobs:
|
|||||||
id: filter_spec_decode
|
id: filter_spec_decode
|
||||||
uses: dorny/paths-filter@v3
|
uses: dorny/paths-filter@v3
|
||||||
with:
|
with:
|
||||||
# speculative decode seems will cause oom issue, disable it now on ci test
|
|
||||||
filters: |
|
filters: |
|
||||||
speculative_tests_changed: 'false'
|
speculative_tests_changed:
|
||||||
|
- ".github/workflows/vllm_ascend_test.yaml"
|
||||||
|
- "tests/singlecard/spec_decode/**"
|
||||||
|
- "tests/multicard/spec_decode_e2e/**"
|
||||||
|
- "vllm_ascend/worker/worker.py"
|
||||||
|
- "vllm_ascend/worker/model_runner.py"
|
||||||
|
- "vllm_ascend/worker/multi_step_runner.py"
|
||||||
|
- "vllm_ascend/worker/multi_step_worker.py"
|
||||||
|
- "vllm_ascend/worker/draft_model_runner.py"
|
||||||
|
- "vllm_ascend/patch/worker/patch_common/patch_metrics.py"
|
||||||
|
- "vllm_ascend/patch/worker/patch_common/patch_spec_decode_worker.py"
|
||||||
|
- "vllm_ascend/patch/worker/patch_common/patch_multi_step_worker.py"
|
||||||
|
|
||||||
- name: Run vllm-project/vllm-ascend Speculative Decode test
|
- name: Run vllm-project/vllm-ascend Speculative Decode test
|
||||||
if: steps.filter_spec_decode.outputs.speculative_tests_changed == 'true' || github.event_name == 'schedule'
|
# speculative decode seems will cause oom issue, only disable it now on ci test with vLLM main
|
||||||
|
if: matrix.vllm_verison == 'v0.8.5' && steps.filter_spec_decode.outputs.speculative_tests_changed == 'true' || github.event_name == 'schedule'
|
||||||
run: |
|
run: |
|
||||||
if [[ "${{ matrix.os }}" == "linux-arm64-npu-1" ]]; then
|
if [[ "${{ matrix.os }}" == "linux-arm64-npu-1" ]]; then
|
||||||
pytest -sv tests/singlecard/spec_decode/e2e/test_mtp_correctness.py # it needs a clean process
|
pytest -sv tests/singlecard/spec_decode/e2e/test_mtp_correctness.py # it needs a clean process
|
||||||
|
|||||||
Reference in New Issue
Block a user