Skip to content

feat: add per-tensor FP8 e4m3 quant/dequant ops for KV cache quantiza… - #1521

Open
BoBoDai wants to merge 2 commits into
InfiniTensor:mainfrom
BoBoDai:suppose-fp8
Open

feat: add per-tensor FP8 e4m3 quant/dequant ops for KV cache quantiza…#1521
BoBoDai wants to merge 2 commits into
InfiniTensor:mainfrom
BoBoDai:suppose-fp8

fix: guard per-tensor FP8 quant against zero scale (all-zero input)

036fb70
Select commit
Loading
Failed to load commit list.

Workflow runs completed with no jobs