Skip to content

An easy-to-use package for implementing SmoothQuant for LLMs

active 2024-02-202026-02-28 (UTC)

Partial coverage17,073 / 21,774 hourly files (78%) · 2 absent upstream · 4,700 failed, retryable2024-02-172026-08-12 (UTC)— sampled evenly across the window, so rankings and trends hold; absolute counts scale up.
Events
80
Pushes
1
Pull requests
4
Issues
6
Stars
44
Forks
6

Activity over time

Daily event counts in the loaded window

Line chart, 740 days from 2024-02-20 to 2026-02-28. Pushes: 1 total, peak 1 in a day. Pull requests: 4 total, peak 1 in a day. Issues: 6 total, peak 1 in a day. Comments: 15 total, peak 2 in a day. Stars: 44 total, peak 2 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
AniZpZ12127
ponytaill4013
huangtingwei99883011
DonliFly1000
gesanqiu1001
Flyipig1000
AlexMa01001
wanto-rest1001
HandH19981000
AGI-player1000
MingLin-home1000
peilin-chen1000
shengqihailuo11001

Recent activity

Latest issues, pull requests and releases

  • Issue comment#24wanto-rest2025-09-17 03:23
    llama2-7b-chat量化完推理报错
  • Issue comment#25huangtingwei99882025-04-05 08:16
    smoothquant fp8 support
  • Issue comment#24shengqihailuo12025-03-27 03:35
    llama2-7b-chat量化完推理报错
  • Issue#26peilin-chen2024-10-02 18:47
    Can we use W8A8B8O8Linear in LLaMA model?
  • Pull request#25huangtingwei99882024-08-24 11:21
  • Issue comment#14gesanqiu2024-07-22 04:07
    Tensor shape error when loading quant Llama-2-70B
  • Issue comment#24AlexMa02024-07-10 06:49
    llama2-7b-chat量化完推理报错
  • Issue comment#22AniZpZ2024-06-14 03:40
    Smoothquant for Phi2 and Qwen2
  • Pull request#22ponytaill2024-05-18 09:17
  • Issue comment#21ponytaill2024-05-18 08:35
    Smoothquant for Phi2
  • Issue comment#21ponytaill2024-05-13 04:28
    Smoothquant for Phi2
  • Issue comment#21ponytaill2024-05-09 04:06
    Smoothquant for Phi2
  • Issue comment#21AniZpZ2024-05-09 03:49
    Smoothquant for Phi2
  • Issue#20Flyipig2024-04-24 03:23
    When quantizing baichuan2-7B, I encountered an error: AttributeError: 'RMSNorm' object has no attribute 'epsilon'.
  • Issue#19AGI-player2024-04-02 02:18
    baichuan2 inference with vllm
  • Pull request#18AniZpZ2024-03-22 02:48
  • Pull request#18AniZpZ2024-03-21 07:43
  • Issue comment#17AniZpZ2024-03-20 07:57
    Maybe some problem you need to take care
  • Issue#17DonliFly2024-03-20 06:16
    Maybe some problem you need to take care
  • Issue comment#15AniZpZ2024-03-11 02:21
    libcudart.so.11.0 error
  • Issue#15huangtingwei99882024-03-10 08:31
    libcudart.so.11.0 error
  • Issue comment#13AniZpZ2024-03-01 02:31
    Any plan for supporting Mistral 7B model?
  • Issue comment#14AniZpZ2024-03-01 02:21
    Tensor shape error when loading quant Llama-2-70B
  • Issue#14MingLin-home2024-02-29 03:10
    Tensor shape error when loading quant Llama-2-70B

Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 44 stars here means stars gained during the window, not the repo's star count.