Skip to content

fix(cuda/quantized): chunk long-prompt qmm launches to avoid gridDim>65535 and int overflow#652

Open
inureyes wants to merge 1 commit into
mainfrom
fix/648-cuda-longprompt-grid-limit
Open

fix(cuda/quantized): chunk long-prompt qmm launches to avoid gridDim>65535 and int overflow#652
inureyes wants to merge 1 commit into
mainfrom
fix/648-cuda-longprompt-grid-limit

fix(cuda/quantized): chunk long-prompt qmm launches to avoid gridDim>…

42c3dbd
Select commit
Loading
Failed to load commit list.