Commit 3d41297
committed
Update base for Update on "Refactor
Summary:
This is to prefer the addition of flashinfer quantize kernel path in next PR
Test Plan:
python test/prototype/mx_formats/test_inference_workflow.py
Reviewers:
Subscribers:
Tasks:
Tags:
[ghstack-poisoned]use_triton_kernel to use nvfp4_quantize_kernel_choice"1 parent b1f18fb commit 3d41297
0 file changed
0 commit comments