Skip to content

ggml: support quant scales for fp8 and nvfp4 - #28898

Draft
0cc4m wants to merge 32 commits into
osimons/ocp_fp8_cudafrom
0cc4m/fp8-scaled-mm
Draft

ggml: support quant scales for fp8 and nvfp4#28898
0cc4m wants to merge 32 commits into
osimons/ocp_fp8_cudafrom
0cc4m/fp8-scaled-mm

Only read scales for valid experts

2895428
Select commit
Loading
Failed to load commit list.

Select a check to view from the sidebar