"...git@developer.sourcefind.cn:kecinstone/2024-pra-vllm.git" did not exist on "48cf1e413c42b29909077afe21c7b9e57996a1cf"
-
Phuong Nguyen authored
* rm cudaGraph compatible trait from GroupedGEMM and groupedQuantize Signed-off-by:
Phuong Nguyen <phuonguyen@nvidia.com> * add grouped_gemm jitting in the unit test Signed-off-by:
Phuong Nguyen <phuonguyen@nvidia.com> --------- Signed-off-by:
Phuong Nguyen <phuonguyen@nvidia.com>
9f9b4816