Adding cuda kernel (optimized for sm80) for block-wise 4b quantized float 16 GEMM. #23421
Triggered via pull request
January 30, 2024 18:36
chenfucn
Status
Success
Total duration
1h 11m 31s
Artifacts
–
windows.yml
on: pull_request
Windows-CUDA-12
34m 45s
Onnxruntime-TVM
1h 11m