Skip to content

Model Compression Toolbox for Large Language Models and Diffusion Models with support to MXFP4

active 2024-11-082025-07-10 (UTC)

Complete coverage26,668 / 26,668 hourly files (100%) · 2 absent upstream2023-08-152026-08-30 (UTC)
Events
642
Pushes
18
Pull requests
10
Issues
74
Stars
354
Forks
36

Activity over time

Daily event counts in the loaded window

Line chart, 245 days from 2024-11-08 to 2025-07-10. Pushes: 18 total, peak 4 in a day. Pull requests: 10 total, peak 5 in a day. Issues: 74 total, peak 4 in a day. Comments: 143 total, peak 13 in a day. Stars: 354 total, peak 29 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
synxlin4911729
lmxyy307015
josephrocca130011
pivtienduc9007
drphero6004
J-Cott5003
yyfcc175004
senlyu1634004
Chenglin-Yang4004
spencergong4022
fishing-pan4003
Lenan224001
yibolu964001
fangg20003001
chuck-ma3002
ShuaiShao933002
samedii3002
George07263003
Manojbhat093001
yachty663003

Recent activity

Latest issues, pull requests and releases

  • Issue#89nvilli2025-07-02 14:31
    SDXL quantization in svdquant
  • Issue#88matrix-yang2025-06-24 06:03
    Question about SVDQuant's design choice for not supporting LLM quantization
  • Issue comment#80DanielLien19842025-06-21 08:47
    Is it difficult to install in a Windows environment?
  • Issue comment#85spencergong2025-06-12 01:02
    feat: Enable multi-GPU support for PTQ
  • Issue comment#87spencergong2025-06-12 01:02
    second change
  • Pull request#87spencergong2025-06-12 01:01
  • Issue comment#49fishing-pan2025-06-11 01:27
    How to quantize flux.1-fill-dev
  • Pull request#84spencergong2025-06-10 11:52
  • Issue#82zero10822025-06-10 10:30
    fp4 for5090
  • Issue#80Neytiri72025-06-03 03:42
    Is it difficult to install in a Windows environment?
  • Issue comment#45Cooper-Ji2025-05-27 09:54
    SVDquant W8A8
  • Issue#75mattam3012025-05-23 02:16
    Smoothquant failed with INT4 quantization
  • Issue#78icyhearts2025-05-21 06:18
    How does smooth_linear_modules ensure the correctness of result when prevs is None?
  • Issue#78icyhearts2025-05-21 06:13
    How does smooth_linear_modules ensure the correctness of result when prevs is None
  • Issue#77Zeqiang-Lai2025-05-02 15:08
    Is there any simple way to quantize a flux-like model ?
  • Issue#76lognat07042025-04-28 19:25
    Does the deepcomposer can be used on SDXL models? Any tech doc for SDXL models?
  • Issue#75mattam3012025-04-27 02:37
    Smoothquant failed with INT4 quantization
  • Issue#74larinius2025-04-25 02:42
    What exact build toolchain for Windows?
  • Issue comment#73nitinmukesh2025-04-22 13:58
    HiDream Support?
  • Issue#73riDuxd2025-04-20 00:07
    HiDream Support?
  • Issue comment#26l2-morreale2025-04-18 11:20
    How to apply SVDQuant for SD3 model?
  • Issue comment#30blacklong282025-04-17 10:11
    torch.OutOfMemoryError: CUDA out of memory
  • Issue comment#30blacklong282025-04-17 10:03
    torch.OutOfMemoryError: CUDA out of memory
  • Issue#72QingshuiL2025-04-15 06:46
    AttributeError: 'NoneType' object has no attribute 'data'
  • Issue#71l2-morreale2025-04-14 13:08
    Diffusion example evaluation

Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 354 stars here means stars gained during the window, not the repo's star count.