Skip to content

Improve layerwise GPTQ memory and speed: Hessian headroom, batch probe and offload fixes - #2945

Open
cjluo-nv wants to merge 4 commits into
mainfrom
chenjiel/gptq-hessian-headroom
Open

Improve layerwise GPTQ memory and speed: Hessian headroom, batch probe and offload fixes#2945
cjluo-nv wants to merge 4 commits into
mainfrom
chenjiel/gptq-hessian-headroom

Keep offloaded layers' quantizer state off the GPU and stop layerwise…

b4a890f
Select commit
Loading
Failed to load commit list.
DCO / DCO succeeded Oct 24, 2026 in 0s

DCO

All commits are signed off!

View more details on DCO