Skip to content

Add optional zero_start_index_M argument to triton fp8 rowwise quantization #8852

Add optional zero_start_index_M argument to triton fp8 rowwise quantization

Add optional zero_start_index_M argument to triton fp8 rowwise quantization #8852

Triggered via pull request January 28, 2025 23:01
Status Success
Total duration 1h 47m 47s
Artifacts 2
generate-matrix  /  generate
4s
generate-matrix / generate
Matrix: build
Fit to window
Zoom out
Zoom in

Artifacts

Produced during runtime
Name Size
pytorch_FBGEMM__3.9_cpu_aarch64
2.69 MB
pytorch_FBGEMM__3.9_cu126_aarch64
446 MB