Connecting fp16xq4 gemm kernels (optimized for A100) to MatMulNBits<fp16> operator #6339
chenfucnsca.yml
on: pull_request
Onnxruntime-SCA-training-CUDA
0s
Onnxruntime-SCA-win32-WINML-x64
0s
Onnxruntime-SCA-win32-WINML-x86
0s
Annotations
3 errors
|
Onnxruntime-SCA-win32-WINML-x86
Canceling since a higher priority waiting request for 'Windows_SCA-cfu_transform_prepack' exists
|
|
Onnxruntime-SCA-training-CUDA
Canceling since a higher priority waiting request for 'Windows_SCA-cfu_transform_prepack' exists
|
|
Onnxruntime-SCA-win32-WINML-x64
Canceling since a higher priority waiting request for 'Windows_SCA-cfu_transform_prepack' exists
|