Skip to content

SCOPE: Optimizing KV Cache Compression in Long-context Generation

active 2024-12-182026-03-01 (UTC)

Complete coverage26,516 / 26,516 hourly files (100%) · 2 absent upstream2023-08-152026-08-23 (UTC)
Events
92
Pushes
18
Pull requests
0
Issues
14
Stars
34
Forks
3

Activity over time

Daily event counts in the loaded window

Line chart, 439 days from 2024-12-18 to 2026-03-01. Pushes: 18 total, peak 7 in a day. Pull requests: 0 total, peak 0 in a day. Issues: 14 total, peak 4 in a day. Comments: 21 total, peak 4 in a day. Stars: 34 total, peak 5 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
Linking-ai3418010
Lueci4er5004
pprp3001
kengchiawu3002
YEOMJINSEOP3001
BigCousin-z2001
NielsRogge2001
callanwu1001

Recent activity

Latest issues, pull requests and releases

  • Issue comment#5YEOMJINSEOP2025-05-09 01:01
    Visualization for Key token selection per Decoding Step
  • Issue#5YEOMJINSEOP2025-05-09 01:01
    Visualization for Key token selection per Decoding Step
  • Issue comment#5Linking-ai2025-05-03 06:03
    Visualization for Key token selection per Decoding Step
  • Issue#1Linking-ai2025-05-01 09:41
    Release SCOPE on Hugging Face
  • Issue#2Linking-ai2025-05-01 09:41
    这个可以和vLLM一起搭配使用吗?优化KV的性能问题?
  • Issue comment#6Lueci4er2025-04-25 12:59
    Potential Misalignment in decoding_indices Generation
  • Issue comment#6Linking-ai2025-04-25 12:51
    Potential Misalignment in decoding_indices Generation
  • Issue comment#6Lueci4er2025-04-25 08:32
    Potential Misalignment in decoding_indices Generation
  • Issue comment#6Lueci4er2025-04-25 03:28
    Potential Misalignment in decoding_indices Generation
  • Issue comment#6Lueci4er2025-04-24 15:16
    Potential Misalignment in decoding_indices Generation
  • Issue#6Lueci4er2025-04-24 15:16
    Potential Misalignment in decoding_indices Generation
  • Issue comment#6callanwu2025-04-24 15:05
    Potential Misalignment in decoding_indices Generation
  • Issue comment#6Linking-ai2025-04-24 14:58
    Potential Misalignment in decoding_indices Generation
  • Issue#5YEOMJINSEOP2025-02-27 07:52
    Key token selection per Decoding Step
  • Issue comment#4pprp2025-01-21 03:48
    Request for release the MMLU and CSQA
  • Issue#4pprp2025-01-21 03:48
    Request for release the MMLU and CSQA
  • Issue comment#1NielsRogge2025-01-20 19:45
    Release SCOPE on Hugging Face
  • Issue comment#4Linking-ai2025-01-20 18:53
    Request for release the MMLU and CSQA
  • Issue comment#4Linking-ai2025-01-20 18:52
    Request for release the MMLU and CSQA
  • Issue#3Linking-ai2025-01-20 18:24
    对attn_weight计算的疑惑
  • Issue#1Linking-ai2025-01-20 18:23
    Release SCOPE on Hugging Face
  • Issue#2Linking-ai2025-01-20 18:21
    这个可以和vLLM一起搭配使用吗?优化KV的性能问题?
  • Issue#3Linking-ai2025-01-20 18:21
    对attn_weight计算的疑惑
  • Issue#4pprp2025-01-18 14:06
    Request for release the MMLU and CSQA
  • Issue comment#3kengchiawu2025-01-08 09:13
    对attn_weight计算的疑惑

Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 34 stars here means stars gained during the window, not the repo's star count.