Skip to content

cuda: raise CUDA graph cache cap from 64 to 512 for tensor parallel - #232

Open
angliubc wants to merge 1 commit into
unslothai:mtp/qwen4exp-nextnfrom
angliubc:fix/cuda-graph-cache-cap-tp
Open

angliubc wants to merge 1 commit into
unslothai:mtp/qwen4exp-nextnfrom
angliubc:fix/cuda-graph-cache-cap-tp

cuda: raise CUDA graph cache cap from 64 to 512 for tensor parallel

d463a1a
Select commit
Loading
Failed to load commit list.