[Core] Disable the chunked prefill feature in Non-MLA LLMs #75
vllm_ascend_test_full.yaml
on: pull_request
changes
4s
Matrix: multicard e2e test - full
Matrix: singlecard e2e test - full
Annotations
1 error
test-full
Canceling since a higher priority waiting request for test-full-refs/pull/2894/merge exists
|