Efficient Triton Kernels for LLM Training
linkedin/Liger-Kernel is drawing steady momentum at +1.3 stars/day (35th percentile in the tracked cohort), for a momentum score of 52.1/100. A recent release is helping fuel the run.
Reconstructed from 245 snapshots — the time-series GitHub’s API doesn’t expose.
Release count rose to 34.
Release count rose to 33.
~10 forks/day, 5.0× the trailing baseline.
Live score, refreshed every 6 hours. Links back to this page.
[](https://repoclimb.com/repo/linkedin/Liger-Kernel)Low breakout odds over the next 14 days, led by push recency (95th pctl) and fork velocity (69th pctl). Confidence is high given the available history.
Transparent heuristic · logged for model training
Percentile rank within the tracked cohort. The score self-calibrates — it answers “accelerating vs. everything else,” not raw size.
Release count rose to 32.
Release count rose to 31.