Adding cuda kernel (optimized for sm80) for block-wise 4b quantized float 16 GEMM. #23417
Triggered via pull request
January 30, 2024 18:20
chenfucn
Status
Cancelled
Total duration
16m 52s
Artifacts
–
windows.yml
on: pull_request
Windows-CUDA-12
10m 38s
Onnxruntime-TVM
16m 32s
Annotations
4 errors
|
Windows-CUDA-12
Canceling since a higher priority waiting request for 'Windows_CI-cfu_kernel' exists
|
|
Windows-CUDA-12
The operation was canceled.
|
|
Onnxruntime-TVM
Canceling since a higher priority waiting request for 'Windows_CI-cfu_kernel' exists
|
|
Onnxruntime-TVM
The operation was canceled.
|