A high-throughput and memory-efficient inference and serving engine for LLMs
vllm-project/vllm is drawing steady momentum at +76.4 stars/day (93rd percentile in the tracked cohort), for a momentum score of 42/100. A recent release is helping fuel the run.
Release count rose to 109.
Release count rose to 108.
Release count rose to 107.
Live score, refreshed every 6 hours. Links back to this page.
[](https://repoclimb.com/repo/vllm-project/vllm)Low breakout odds over the next 14 days, led by star velocity (93th pctl) and fork velocity (98th 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.
Reconstructed from 384 snapshots — the time-series GitHub’s API doesn’t expose.
Release count rose to 106.
Release count rose to 105.
Release count rose to 104.
Release count rose to 103.
Release count rose to 102.
Release count rose to 101.
~144 forks/day, 3.2× the trailing baseline.
Release count rose to 100.
Release count rose to 99.