Skip to content

QuIP - 2-Bit Quantization of Large Language Models.

active 2023-08-162025-03-01 (UTC)

Complete coverage26,585 / 26,585 hourly files (100%) · 2 absent upstream2023-08-152026-08-26 (UTC)
Events
161
Pushes
4
Pull requests
1
Issues
15
Stars
119
Forks
9

Activity over time

Daily event counts in the loaded window

Line chart, 564 days from 2023-08-16 to 2025-03-01. Pushes: 4 total, peak 1 in a day. Pull requests: 1 total, peak 1 in a day. Issues: 15 total, peak 2 in a day. Comments: 11 total, peak 4 in a day. Stars: 119 total, peak 20 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
jerry-chee224110
yanni-code3000
xwuShirley2000
yzl-eup1001
ozzzp1000
yachty661000
Ottovonxu1000

Recent activity

Latest issues, pull requests and releases

  • Issue comment#11jerry-chee2023-12-06 22:09
    Why only class Quant3Linear(nn.Module)? Does this work for 2bit, 3bit, and 4bit? I understand it is only for bit3 . Thanks
  • Issue#11jerry-chee2023-12-06 22:09
    Why only class Quant3Linear(nn.Module)? Does this work for 2bit, 3bit, and 4bit? I understand it is only for bit3 . Thanks
  • Issue#10jerry-chee2023-12-06 22:08
    4bit or 2bit quantization model saved is fp 16, I am confused。Thank you
  • Issue#11yanni-code2023-11-16 03:27
    Why only class Quant3Linear(nn.Module)? Does this work for 2bit, 3bit, and 4bit? I understand it is only for bit3 . Thanks
  • Issue#10yanni-code2023-11-14 07:25
    4bit or 2bit quantization model saved is fp 16, I am confused。Thank you
  • Issue#9jerry-chee2023-10-31 21:09
    Thank you
  • Issue comment#8jerry-chee2023-10-31 21:08
    support for llama
  • Issue#8jerry-chee2023-10-31 21:08
    support for llama
  • Issue#9yanni-code2023-10-24 12:56
    which file is the quantization method of QuIP? Thank you
  • Issue#8Ottovonxu2023-09-27 16:27
    support for llama
  • Issue comment#7jerry-chee2023-09-19 04:10
    Do we still need to store U, V for each W
  • Issue#7jerry-chee2023-09-19 04:10
    Do we still need to store U, V for each W
  • Issue#7xwuShirley2023-09-04 23:49
    Do we still need to store U, V for each W
  • Issue comment#4jerry-chee2023-09-04 19:55
    How to use quantized model on inference
  • Issue comment#5jerry-chee2023-09-04 19:38
    error computing is not correct of covariant of pre and post process
  • Issue comment#6jerry-chee2023-09-04 19:26
    group-size for quip
  • Issue#6jerry-chee2023-09-04 19:26
    group-size for quip
  • Issue comment#6jerry-chee2023-09-04 19:24
    group-size for quip
  • Issue#6xwuShirley2023-09-03 04:52
    group-size for quip
  • Issue#5ozzzp2023-08-28 01:47
    error computing is not correct of covariant of pre and post process
  • Issue comment#2jerry-chee2023-08-24 20:01
    Evaluation on LLama
  • Issue#2jerry-chee2023-08-24 20:01
    Evaluation on LLama
  • Issue comment#2jerry-chee2023-08-24 20:01
    Evaluation on LLama
  • Issue#4yachty662023-08-22 16:42
    How to use quantized model for inference
  • Issue comment#3jerry-chee2023-08-21 03:17
    Fix typo in README.md

Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 119 stars here means stars gained during the window, not the repo's star count.