Skip to content

🎯An accuracy-first, highly efficient quantization toolkit for LLMs, designed to minimize quality degradation across Weight-Only Quantization, MXFP4, NVFP4, GGUF, and adaptive schemes.

Python Β· active 2024-01-04 β†’ 2026-09-24 (UTC)

Complete coverage27,294 / 27,297 hourly files (100%) Β· 2 absent upstream2023-08-15 β†’ 2026-09-25 (UTC)
Events
15K
Pushes
5.4K
Pull requests
1.4K
Issues
787
Stars
694
Forks
67

Activity over time

Daily event counts in the loaded window

Line chart, 995 days from 2024-01-04 to 2026-09-24. Pushes: 5,439 total, peak 38 in a day. Pull requests: 1,426 total, peak 19 in a day. Issues: 787 total, peak 20 in a day. Comments: 2,695 total, peak 26 in a day. Stars: 694 total, peak 26 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 β€” βˆ’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 β€” stars and forks excluded, so this is contribution rather than popularity

ContributorContributionsPushesPRsComments
wenhuach215.2K1.7K6471.3K
n1ck-guo1.3K843163115
WeiweiZhang1994463214113
yiliu3076237577150
xin3he73034165136
pre-commit-ci[bot]65464950
Copilot6307019330
XuehaoSun3852525122
chensuyue3361944228
mengniwang952061021846
lvliang-intel1631031128
yintong-lu13393185
azure-pipelines[bot]860086
Kaihui-intel76361313
hshen145211016
zhewang1-intc480224
luoyu-intel472735
Zhenzhong1403514
lkk12014402400520
Tortoise17300017

Recent activity

Latest issues, pull requests and releases

Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals β€” 694 stars here means stars gained during the window, not the repo's star count.