Skip to content

Update MSLK Triton FP8 row quantization kernel to match CUDA arithmetic and delete the C++ quantize_fp8_per_row kernel (#224) #852

Update MSLK Triton FP8 row quantization kernel to match CUDA arithmetic and delete the C++ quantize_fp8_per_row kernel (#224)

Update MSLK Triton FP8 row quantization kernel to match CUDA arithmetic and delete the C++ quantize_fp8_per_row kernel (#224) #852

This workflow is awaiting approval from a maintainer in #224
Triggered via pull request March 13, 2026 22:46
Status Action required
Total duration
Artifacts
This workflow is awaiting approval from a maintainer in #224
generate-matrix  /  generate
generate-matrix / generate
filter-matrix
filter-matrix
Matrix: build
Waiting for pending jobs
Fit to window
Zoom out
Zoom in