tools · linkedin

Liger Kernel

Triton kernels for LLM training that fuse common sequences — RMSNorm, RoPE, SwiGLU, and a chunked fused linear cross-entropy — to cut activation memory and kernel-launch overhead. The fused cross-entropy is the notable one: it avoids materialising the full logits tensor, which is the dominant activation cost at large vocabularies.

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

Publisherlinkedin
OriginUnited States
LicenceBSD-2-Clause

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.