Skip to content

nunchaku-tech/deepcompressor

View on GitHub ↗Related repositories →

Model Compression Toolbox for Large Language Models and Diffusion Models

active 2025-07-162026-01-08 (UTC)

Complete coverage26,750 / 26,750 hourly files (100%) · 2 absent upstream2023-08-152026-09-02 (UTC)
Events
153
Pushes
0
Pull requests
2
Issues
8
Stars
99
Forks
11

Activity over time

Daily event counts in the loaded window

Line chart, 177 days from 2025-07-16 to 2026-01-08. Pushes: 0 total, peak 0 in a day. Pull requests: 2 total, peak 1 in a day. Issues: 8 total, peak 1 in a day. Comments: 29 total, peak 4 in a day. Stars: 99 total, peak 3 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
rwfsmith6006
lantudou3021
Ph0rk0z3003
Leo-A11A3003
6310682642001
eyaler2001
andrsatalia2001
otherV2002
AuZhoomLee2002
moveforever2002
karolistamutis1001
Skydoge-zjm1001
weichenyisu1001
pingzhili1001
Orlando-CS1001
lisuying2141000
xuhongtao0011000
QQQ271000
mamorett1001
nvilli1001

Recent activity

Latest issues, pull requests and releases

  • Issue comment#108eyaler2026-01-08 13:47
    sdxl-turbo colab inside + questions
  • Issue comment#108Skydoge-zjm2026-01-08 06:21
    sdxl-turbo colab inside + questions
  • Pull request#115lantudou2025-12-24 08:38
  • Issue comment#103rwfsmith2025-12-16 07:49
    SVDQuant for WAN 2.2
  • Issue#113lisuying2142025-12-05 05:18
    [bug] of convert llama-30b using lmquant.llm.run
  • Issue comment#49karolistamutis2025-12-03 17:30
    How to quantize flux.1-fill-dev
  • Issue comment#111otherV2025-11-28 08:22
    Perf: Replace full SVD with torch.svd_lowrank for acceleration
  • Issue comment#111lantudou2025-11-28 05:58
    Perf: Replace full SVD with torch.svd_lowrank for acceleration
  • Pull request#111lantudou2025-11-26 06:23
  • Issue comment#108otherV2025-11-14 21:15
    sdxl-turbo colab inside + questions
  • Issue#108eyaler2025-11-10 22:46
    sdxl-turbo colab inside + questions
  • Issue comment#104mamorett2025-11-06 19:10
    Qwen-Image/Edit quantization code open source
  • Issue comment#94weichenyisu2025-10-17 06:34
    FLUX Dev Quantization fails on an A100 with 40 GB VRAM
  • Issue#106QQQ272025-10-17 02:38
    Regarding quantization parameter adjustment
  • Issue#104xuhongtao0012025-09-19 08:26
    Qwen-Image/Edit quantization code open source
  • Issue comment#66Ph0rk0z2025-09-18 22:02
    Batch sizes for 24gb gpu
  • Issue comment#66rwfsmith2025-09-18 18:40
    Batch sizes for 24gb gpu
  • Issue comment#66Ph0rk0z2025-09-18 11:39
    Batch sizes for 24gb gpu
  • Issue comment#66rwfsmith2025-09-18 04:06
    Batch sizes for 24gb gpu
  • Issue comment#66rwfsmith2025-09-17 23:55
    Batch sizes for 24gb gpu
  • Issue comment#66rwfsmith2025-09-17 22:02
    Batch sizes for 24gb gpu
  • Issue comment#100Leo-A11A2025-09-12 03:27
    Quantize Flux.1-kontext
  • Issue comment#1006310682642025-09-10 02:37
    Quantize Flux.1-kontext
  • Issue comment#66Ph0rk0z2025-09-09 22:34
    Batch sizes for 24gb gpu
  • Issue comment#66rwfsmith2025-09-09 21:17
    Batch sizes for 24gb gpu

Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 99 stars here means stars gained during the window, not the repo's star count.