Skip to content
Back to pull request #18619

Adding cuda kernel (optimized for sm80) for block-wise 4b quantized float 16 GEMM. #21834

Sign in to view logs

Adding cuda kernel (optimized for sm80) for block-wise 4b quantized float 16 GEMM.

Adding cuda kernel (optimized for sm80) for block-wise 4b quantized float 16 GEMM. #21834

Run time

Learn about OS pricing on GitHub Actions
Job Run time
Analyze (java)
2m 25s
Analyze (javascript)
2m 7s
Analyze (python)
5m 10s
9m 42s