Skip to content

feat: add FP8 blockwise weight quantization and FP8(E4M3) KV cache support - #586

Open
shsaihdsaiudh wants to merge 4 commits into
InfiniTensor:mainfrom
shsaihdsaiudh:feat/fp8-blockwise-quantization
Open

feat: add FP8 blockwise weight quantization and FP8(E4M3) KV cache support#586
shsaihdsaiudh wants to merge 4 commits into
InfiniTensor:mainfrom
shsaihdsaiudh:feat/fp8-blockwise-quantization

Commits

Commits on Sep 20, 2026