Skip to content

The official implementation of the ICML 2023 paper OFQ-ViT

active 2023-08-162025-11-04 (UTC)

Complete coverage26,471 / 26,471 hourly files (100%) · 2 absent upstream2023-08-152026-08-21 (UTC)
Events
46
Pushes
4
Pull requests
0
Issues
9
Stars
22
Forks
4

Activity over time

Daily event counts in the loaded window

Line chart, 812 days from 2023-08-16 to 2025-11-04. Pushes: 4 total, peak 3 in a day. Pull requests: 0 total, peak 0 in a day. Issues: 9 total, peak 4 in a day. Comments: 7 total, peak 1 in a day. Stars: 22 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
nbasyl13404
temporydan2001
jiho2641001
brisker1000
dashangyanhua1001
techmonsterwang1000
LuletterSoul1000

Recent activity

Latest issues, pull requests and releases

  • Issue comment#4jiho2642025-06-26 06:57
    The +0.5 term in StatQ results in asymmetric weight quantization.
  • Issue comment#4dashangyanhua2025-04-16 16:08
    The +0.5 term in StatQ results in asymmetric weight quantization.
  • Issue#3nbasyl2024-04-20 12:37
    Toy example
  • Issue#2nbasyl2024-04-20 12:37
    Is there any analysis on the oscillation problem on the activation quantization?
  • Issue#1nbasyl2024-04-20 12:37
    Does mixed precision training greatly affect performance?
  • Issue#5nbasyl2024-04-20 12:36
    The activation was never quantized in the code OR WaS iT?
  • Issue comment#5temporydan2024-02-24 03:59
    The activation was never quantized in the code OR WaS iT?
  • Issue comment#5nbasyl2024-02-23 17:29
    The activation was never quantized in the code
  • Issue#5temporydan2024-02-16 19:45
    The activation was never quantized in the code
  • Issue#4LuletterSoul2024-01-30 06:41
    The +0.5 term in StatQ results in asymmetric weight quantization.
  • Issue comment#3nbasyl2023-11-23 10:24
    Toy example
  • Issue#3techmonsterwang2023-11-19 04:42
    Toy example
  • Issue comment#1nbasyl2023-09-02 06:50
    Does mixed precision training greatly affect performance?
  • Issue#1nbasyl2023-09-02 06:50
    Does mixed precision training greatly affect performance?
  • Issue comment#2nbasyl2023-08-29 08:14
    Is there any analysis on the oscillation problem on the activation quantization?
  • Issue#2brisker2023-08-21 02:45
    Is there any analysis on the oscillation problem on the activation quantization?

Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 22 stars here means stars gained during the window, not the repo's star count.