Skip to content

perf(prefill): MoE prefill CUDA-graph capture — +9-27% pp512 on NVFP4#179

Merged
kekzl merged 1 commit into
mainfrom
perf/prefill-graphs-prewarm-fix
May 15, 2026
Merged

perf(prefill): MoE prefill CUDA-graph capture — +9-27% pp512 on NVFP4#179
kekzl merged 1 commit into
mainfrom
perf/prefill-graphs-prewarm-fix

Commits

Commits on May 15, 2026