FlashInfer: Kernel Library for LLM Serving
FlashInfer is a library and kernel generator that supplies GPU operations used to run large language model inference, including attention, matrix multiplication, and mixture-of-experts computations. It helps engineers build and optimize LLM serving systems across supported GPU hardware and backend implementations. Its catalogue add-ons provide skills and instructions for working with FlashInfer.
This repository also configures its own agents. See what flashinfer tells them →
Skill Claude CodeCodex
The explicit GenPhase prototype is independently owned by ../nextcutedslmegamoe. This legacy package lazily re-exports its six public GenPhase names. Follow that package's update workflow for GenPhase changes; keep this older snapshot separate. The default backend heuristics do not select GenPhase automatically.
Skill Claude CodeCodex
This tree vendors the kernel team's SM90 FP8 MegaMoE drop — a fork of the same kernel repo that kernelsrc/sm100/cutedslmegamoe vendors (Bangyu's SM100 tree). The SM90 work (Vincent's hoppermegamoe branch) moved the shared runtime forward, so this tree duplicates common/, src/, and moenvfp4swapab/ at its own revision…
Skill Claude CodeCodex
Skill "swapab_cutedsl_megakernel" from flashinfer-ai/flashinfer, covering updating the sm120 swap-ab cutedsl megamoe kernel src, layout, when the kernel team drops a new version of src/ and what not to update here.
Skill Claude CodeCodex
Read VENDOR.md for the exact integration baseline, namespace mapping and local device differences. This package is independently owned by SM100/103; keep the original Rubin tree and frontend unchanged.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: