tools · flashinfer-ai

FlashInfer

Attention kernel library built for inference serving rather than training: paged and ragged KV-cache layouts, batched prefill and decode kernels, and CUDA-graph-friendly execution. Adopted as a kernel backend by several serving stacks, so it sits underneath the engines rather than beside them.

Verify

What this registry has checked

Quarantine. We hold the publisher’s own published hash for these weights and have recorded it against this entry. We have not downloaded and hashed the weights ourselves, so the hash is the publisher’s claim, not our measurement.
Re-check this yourself → Source → Full record →

What is recorded

Publisherflashinfer-ai
OriginUnited States
LicenceApache-2.0

Elsewhere in the registry

All tools → Browse with filters → What will run on my hardware? →

Registry record as of 2026-08-14. Identity, licence and parameter count are properties of a release and do not move; tier can, and the verify link above re-checks it against the live registry rather than this page.