Skip to content

[None][feat] Add calibrated INT8 KV cache to PyTorch backend - #18953

Open
zupengwang wants to merge 2 commits into
NVIDIA:mainfrom
zupengwang:codex/pytorch-int8-kv-cache
Open

zupengwang wants to merge 2 commits into
NVIDIA:mainfrom
zupengwang:codex/pytorch-int8-kv-cache