Skip to content
Back to pull request #18619

Adding cuda kernel (optimized for sm80) for block-wise 4b quantized float 16 GEMM. #24358

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. #24358

Triggered via pull request February 28, 2024 23:40
@chenfucnchenfucn
synchronize #18619
chenfucn:cfu_kernel
Status Success
Total duration 1h 12m 47s
Artifacts –

windows.yml

on: pull_request
Windows-CUDA-12
53m 14s
Windows-CUDA-12
Onnxruntime-TVM
1h 12m
Onnxruntime-TVM
Fit to window
Zoom out
Zoom in