"git@developer.sourcefind.cn:kecinstone/2024-pra-vllm.git" did not exist on "c3442c1f6fabe54adb82d2d676920c5f31b9834e"
-
Hongbin Liu authored
avoid redundant computation for cu_seqlens Signed-off-by:
Hongbin Liu <hongbinl@nvidia.com> Co-authored-by:
Hongbin Liu <hongbinl@nvidia.com> Co-authored-by:
Tim Moon <4406448+timmoon10@users.noreply.github.com>
fad3044b