New GEMM kernels for weight-only quantization #877
Annotations
4 errors
cuda-11.8
Canceling since a higher priority waiting request for 'linux-x64-gpu-refs/pull/2090/merge' exists
|
cuda-11.8
The operation was canceled.
|
cuda-12.1
Canceling since a higher priority waiting request for 'linux-x64-gpu-refs/pull/2090/merge' exists
|
cuda-12.1
The operation was canceled.
|