Actions: vllm-project/vllm-ascend
Actions
7,287 workflow runs
7,287 workflow runs
seq_lens CPU cache to avoid frequent d2h copy for better performance
E2E-Full
#7289:
Pull request #6448
labeled
by
shen-shanshan
seq_lens CPU cache to avoid frequent d2h copy for better performance
E2E-Full
#7288:
Pull request #6448
labeled
by
shen-shanshan