Skip to content

A unified library of SOTA model optimization techniques like quantization, pruning, distillation, speculative decoding, etc. It compresses deep learning models for downstream deployment frameworks like TensorRT-LLM, TensorRT, vLLM, etc. to optimize inference speed.

active 2025-12-07 → 2026-09-25 (UTC)

Complete coverage27,313 / 27,313 hourly files (100%) · 2 absent upstream2023-08-15 → 2026-09-26 (UTC)
Events
12.7K
Pushes
5.8K
Pull requests
419
Issues
144
Stars
300
Forks
61

Activity over time

Daily event counts in the loaded window

Line chart, 293 days from 2025-12-07 to 2026-09-25. Pushes: 5,808 total, peak 123 in a day. Pull requests: 419 total, peak 29 in a day. Issues: 144 total, peak 10 in a day. Comments: 2,621 total, peak 179 in a day. Stars: 300 total, peak 8 in a day.

  • Pushes
  • Pull requests
  • Issues
  • Comments
  • Stars

Stars, PRs, issues and forks are under-captured in the later part of this window. GH Archive progressively stopped capturing non-push events during 2026 — −95% or worse by the end of the window. Every series here except Pushes fades for that reason, so a decline above reflects the archive, not this repository. Pushes stay reliable throughout, so read them, and the contributor counts derived from them, as the real signal. Data health has the measurements.

Top contributors

Pushes, PRs, issues, reviews and comments — stars and forks excluded, so this is contribution rather than popularity

ContributorContributionsPushesPRsComments
copy-pr-bot[bot]1.8K1.7K0114
github-actions[bot]1.5K1.4K9109
coderabbitai[bot]1.2K41669
kevalmorabia9768639035130
realAsma44610212159
cjluo-nv43411022159
h-guo183351962748
ChenhanYu3132002347
claude[bot]29500119
kaix-nv2531142467
shengliangxu2521441053
ajrasane237921295
jingyu-ml2321492229
meenchen2231011557
danielkorzekwa211161829
Edwardf0t1207871160
yeyu-nvidia2041401228
willg-nv15201072
codecov[bot]14900149
kinjalpatel2714985727

Recent activity

Latest issues, pull requests and releases

Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 300 stars here means stars gained during the window, not the repo's star count.