Skip to content

Adds skip-softmax calibration through the vLLM serving path#1992

Draft
kaix-nv wants to merge 8 commits into
mainfrom
kaix/vllm_skip_calib_upstream
Draft

Adds skip-softmax calibration through the vLLM serving path#1992
kaix-nv wants to merge 8 commits into
mainfrom
kaix/vllm_skip_calib_upstream

Address review round 2: close remaining skip+quant routes and edge cases

950d2f0
Select commit
Loading
Failed to load commit list.
DCO / DCO succeeded Jul 20, 2026 in 0s

DCO

All commits are signed off!

View more details on DCO