Skip to content

Layer-Condensed KV cache w/ 10 times larger batch size, fewer params and less computation. Dramatic speed up with better task performance. Accepted to ACL 2024.

active 2024-05-202025-11-10 (UTC)

Complete coverage26,459 / 26,459 hourly files (100%) · 2 absent upstream2023-08-152026-08-21 (UTC)
Events
297
Pushes
55
Pull requests
9
Issues
19
Stars
146
Forks
11

Activity over time

Daily event counts in the loaded window

Line chart, 540 days from 2024-05-20 to 2025-11-10. Pushes: 55 total, peak 9 in a day. Pull requests: 9 total, peak 5 in a day. Issues: 19 total, peak 2 in a day. Comments: 44 total, peak 8 in a day. Stars: 146 total, peak 35 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
why-in-Shanghaitech8655921
SpoSer2311005
ChenHong309005
Mostafa-Emad778006
pigdogbaby6006
311dada3001
Draconis982000
alvi751000
123shivanshukumar1000

Recent activity

Latest issues, pull requests and releases

  • Issue#17Draconis982025-07-13 12:06
    Missing torch dependency for flash-attn in requirements.txt
  • Issue#17Draconis982025-07-13 05:33
    Missing torch dependency for flash-attn in requirements.txt
  • Issue#16123shivanshukumar2025-06-21 14:03
    KV computation during inference
  • Issue#12ChenHong302025-02-21 07:02
    Question about supporting other settings of cross-layer KV cache sharing
  • Issue comment#15why-in-Shanghaitech2024-12-25 10:58
    Layer Types Configuration Intuition
  • Issue#14SpoSer232024-12-12 13:42
    Is training from scratch essential?
  • Issue comment#14why-in-Shanghaitech2024-12-10 01:11
    Is training from scratch essential?
  • Issue comment#14SpoSer232024-12-09 13:12
    Is training from scratch essential?
  • Issue comment#14why-in-Shanghaitech2024-12-09 00:28
    Is training from scratch essential?
  • Issue#14SpoSer232024-12-08 21:07
    Is training from scratch essential?
  • Issue#13SpoSer232024-12-05 22:30
    use_sequential flag in training
  • Issue comment#13pigdogbaby2024-12-05 03:13
    use_sequential flag in training
  • Issue#13SpoSer232024-12-04 11:49
    use_sequential flag in training
  • Issue comment#11Mostafa-Emad772024-12-03 11:38
    Guidance on Fine-Tuning Llama in LCKV Framework
  • Issue#11Mostafa-Emad772024-12-03 11:38
    Guidance on Fine-Tuning Llama in LCKV Framework
  • Issue comment#11why-in-Shanghaitech2024-12-02 02:03
    Guidance on Fine-Tuning Llama in LCKV Framework
  • Issue comment#11why-in-Shanghaitech2024-12-01 11:08
    Guidance on Fine-Tuning Llama in LCKV Framework
  • Issue comment#11why-in-Shanghaitech2024-12-01 10:59
    Guidance on Fine-Tuning Llama in LCKV Framework
  • Issue comment#10Mostafa-Emad772024-12-01 10:36
    What is the specific version of the Python this project running on?
  • Issue comment#11Mostafa-Emad772024-12-01 09:11
    Guidance on Fine-Tuning Llama in LCKV Framework
  • Issue comment#11why-in-Shanghaitech2024-11-28 14:10
    Guidance on Fine-Tuning Llama in LCKV Framework
  • Issue comment#11why-in-Shanghaitech2024-11-21 02:01
    Guidance on Fine-Tuning Llama in LCKV Framework
  • Issue comment#11Mostafa-Emad772024-11-20 15:03
    Guidance on Fine-Tuning Llama in LCKV Framework
  • Issue comment#11why-in-Shanghaitech2024-11-20 12:19
    Guidance on Fine-Tuning Llama in LCKV Framework
  • Issue comment#11Mostafa-Emad772024-11-20 11:00
    Guidance on Fine-Tuning Llama in LCKV Framework

Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 146 stars here means stars gained during the window, not the repo's star count.