Skip to content

QuEST: Efficient Finetuning for Low-bit Diffusion Models

active 2024-03-312026-05-06 (UTC)

Partial coverage16,459 / 20,760 hourly files (79%) · 2 absent upstream · 4,300 failed, retryable2024-03-302026-08-12 (UTC)— sampled evenly across the window, so rankings and trends hold; absolute counts scale up.
Events
85
Pushes
16
Pull requests
0
Issues
12
Stars
20
Forks
1

Activity over time

Daily event counts in the loaded window

Line chart, 767 days from 2024-03-31 to 2026-05-06. Pushes: 16 total, peak 4 in a day. Pull requests: 0 total, peak 0 in a day. Issues: 12 total, peak 2 in a day. Comments: 34 total, peak 6 in a day. Stars: 20 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
hatchetProject3316016
Yheechou7006
mason59576004
seung-hoon-lee5002
ccj53513002
DHKim04283001
csguoh2001
YangYang-DLUT2001
cantbebetter21001

Recent activity

Latest issues, pull requests and releases

  • Issue comment#19ccj53512025-01-24 06:22
    Run post_layer_recon_sd.py got RuntimeError: One of the differentiated Tensors does not require grad
  • Issue comment#19hatchetProject2025-01-22 03:07
    Run post_layer_recon_sd.py got RuntimeError: One of the differentiated Tensors does not require grad
  • Issue comment#19ccj53512025-01-22 02:54
    Run post_layer_recon_sd.py got RuntimeError: One of the differentiated Tensors does not require grad
  • Issue comment#19hatchetProject2025-01-22 02:20
    Run post_layer_recon_sd.py got RuntimeError: One of the differentiated Tensors does not require grad
  • Issue#19ccj53512025-01-22 01:57
    Run post_layer_recon_sd.py got RuntimeError: One of the differentiated Tensors does not require grad
  • Issue#18seung-hoon-lee2024-12-16 05:50
    Quantizer implementation error?
  • Issue comment#18seung-hoon-lee2024-12-16 05:50
    Quantizer implementation error?
  • Issue comment#18hatchetProject2024-12-16 05:26
    Quantizer implementation error?
  • Issue#18seung-hoon-lee2024-12-16 04:31
    Quantizer implementation error?
  • Issue#14Yheechou2024-07-04 07:17
    About w4a4 calibration model
  • Issue comment#14Yheechou2024-07-04 05:10
    About w4a4 calibration model
  • Issue comment#14hatchetProject2024-07-04 03:50
    About w4a4 calibration model
  • Issue comment#14Yheechou2024-07-04 03:41
    About w4a4 calibration model
  • Issue comment#14hatchetProject2024-07-04 03:24
    About w4a4 calibration model
  • Issue comment#14Yheechou2024-07-04 01:59
    About w4a4 calibration model
  • Issue comment#14hatchetProject2024-07-04 00:02
    About w4a4 calibration model
  • Issue comment#15YangYang-DLUT2024-07-02 03:02
    Simulated quantization or actual quantization?
  • Issue#15YangYang-DLUT2024-07-02 02:57
    Simulated quantization or actual quantization?
  • Issue comment#14hatchetProject2024-07-01 03:56
    About w4a4 calibration model
  • Issue comment#14Yheechou2024-07-01 03:34
    About w4a4 calibration model
  • Issue comment#14Yheechou2024-07-01 03:31
    About w4a4 calibration model
  • Issue comment#14Yheechou2024-07-01 03:31
    About w4a4 calibration model
  • Issue comment#11seung-hoon-lee2024-06-12 06:54
    Code looks like QKMatmul and SMVMatmul calculates with full precision matrix multiplication.
  • Issue comment#11hatchetProject2024-06-12 06:09
    Code looks like QKMatmul and SMVMatmul calculates with full precision matrix multiplication.
  • Issue#11seung-hoon-lee2024-06-12 05:11
    Code looks like QKMatmul and SMVMatmul calculates with full precision matrix multiplication.

Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 20 stars here means stars gained during the window, not the repo's star count.