Actions: vllm-project/vllm-ascend
Actions
16 workflow runs
16 workflow runs
seq_lens CPU cache to avoid frequent d2h copy for better performance
Nightly-A2
#15:
Pull request #6448
labeled
by
shen-shanshan
seq_lens CPU cache to avoid frequent d2h copy for better performance
Nightly-A2
#14:
Pull request #6448
labeled
by
shen-shanshan