"...git@developer.sourcefind.cn:kecinstone/2024-pra-vllm.git" did not exist on "64e0e383148a613c327d4bf9e866b7a185df8277"
-
Phuong Nguyen authored
* shardy + quantize_layout rework Signed-off-by:
Phuong Nguyen <phuonguyen@nvidia.com> * add assertion for NVFP4 in fused act and fused norm primitive Signed-off-by:
Phuong Nguyen <phuonguyen@nvidia.com> * add assertions Signed-off-by:
Phuong Nguyen <phuonguyen@nvidia.com> --------- Signed-off-by:
Phuong Nguyen <phuonguyen@nvidia.com>
9440b76a