Skip to content

ML Sys project, forked from SnapKV

Python · active 2024-12-282026-04-18 (UTC)

Partial coverage12,560 / 14,269 hourly files (88%) · 2 absent upstream · 1,703 failed, retryable2024-12-242026-08-11 (UTC)— sampled evenly across the window, so rankings and trends hold; absolute counts scale up.
Events
76
Pushes
1
Pull requests
1
Issues
4
Stars
49
Forks
14

Activity over time

Daily event counts in the loaded window

Line chart, 477 days from 2024-12-28 to 2026-04-18. Pushes: 1 total, peak 1 in a day. Pull requests: 1 total, peak 1 in a day. Issues: 4 total, peak 1 in a day. Comments: 7 total, peak 3 in a day. Stars: 49 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
Ppaddington3002
Lueci4er2001
wrnwwrnw2002
Arist121000
LiJunscs1000
XiongxiaoL1001
PengWenChen1001
Clement251010
WendyH11081100

Recent activity

Latest issues, pull requests and releases

  • Pull request#32Clement252025-08-09 09:44
  • Issue comment#29Ppaddington2025-07-29 11:51
    Repeated k/v eliminates GQA advantage and full attention in the prefill stage
  • Issue comment#11Ppaddington2025-07-29 11:47
    why only decode do compress?
  • Issue comment#31wrnwwrnw2025-06-19 06:55
    Confusion in Selecting Indices
  • Issue comment#31Lueci4er2025-06-19 06:54
    Confusion in Selecting Indices
  • Issue comment#31wrnwwrnw2025-06-19 06:49
    Confusion in Selecting Indices
  • Issue#31Lueci4er2025-04-25 05:59
    Confusion in Selecting Indices
  • Issue#29Ppaddington2025-03-21 04:29
    Repeated k/v eliminates GQA advantage and full attention in the prefill stage
  • Issue#25Arist122025-02-26 03:55
    why not use the last token for kv cache compression
  • Issue#28LiJunscs2025-01-10 04:40
    Bug on Qwen2-VL
  • Issue comment#27PengWenChen2025-01-07 06:21
    The first generation token output sees the whole cache key and value
  • Issue comment#27XiongxiaoL2025-01-07 03:18
    The first generation token output sees the whole cache key and value

Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 49 stars here means stars gained during the window, not the repo's star count.