[Core] Disable the chunked prefill feature in Non-MLA LLMs #12221
Triggered via pull request
September 12, 2025 10:05
rjg-lyh
Status
Cancelled
Total duration
5m 49s
Artifacts
–
vllm_ascend_test.yaml
on: pull_request
Matrix: singlecard e2e test - light
Matrix: unit test
Matrix: multicard e2e test - light
Annotations
5 errors
|
lint / pre-commit
The operation was canceled.
|
|
Ruff (E712):
vllm_ascend/platform.py#L149
vllm_ascend/platform.py:149:21: E712 Avoid equality comparisons to `True`; use `if ascend_scheduler_config.enable_chunked_prefill:` for truth checks
|
|
lint / pre-commit
Canceling since a higher priority waiting request for test-refs/pull/2894/merge exists
|
|
test
Canceling since a higher priority waiting request for test-refs/pull/2894/merge exists
|
|
test
Canceling since a higher priority waiting request for test-refs/pull/2894/merge exists
|