Skip to content

πŸ”₯ Flame: Flash linear attention made easy πŸš€

Python Β· active 2025-01-06 β†’ 2026-05-28 (UTC)

Complete coverage26,565 / 26,565 hourly files (100%) Β· 2 absent upstream2023-08-15 β†’ 2026-08-25 (UTC)
Events
650
Pushes
144
Pull requests
31
Issues
43
Stars
224
Forks
32

Activity over time

Daily event counts in the loaded window

Line chart, 508 days from 2025-01-06 to 2026-05-28. Pushes: 144 total, peak 13 in a day. Pull requests: 31 total, peak 3 in a day. Issues: 43 total, peak 3 in a day. Comments: 128 total, peak 12 in a day. Stars: 224 total, peak 8 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 β€” βˆ’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 β€” stars and forks excluded, so this is contribution rather than popularity

Recent activity

Latest issues, pull requests and releases

  • Issue comment#49coderabbitai[bot]2026-01-14 17:15
    Fix resharding bug when dataset variable is reassigned
  • Pull request#48CarlOwOs2026-01-01 13:02
  • Issue#43github-actions[bot]2025-12-28 00:52
    [Bug] load config error
  • Issue comment#43github-actions[bot]2025-12-28 00:52
    [Bug] load config error
  • Issue#43github-actions[bot]2025-12-14 00:49
    [Bug] load config error
  • Issue#47pprp2025-12-02 02:18
    [Bug] RMSNorm parameters stay at 1 and do not update
  • Issue#47pprp2025-12-01 10:13
    [Bug] When training GLA, the parameter of RMSNorm remain all 1 and didn't get updated
  • Issue#47pprp2025-11-29 03:26
    [Bug] When training GLA, the parameter of RMSNorm remain all 1 and didn't get updated
  • Issue#47pprp2025-11-29 03:26
    [Bug] When training GLA, the parameter of RMSNorm remain all 1 and didn't get updated
  • Issue comment#46gemini-code-assist[bot]2025-11-15 16:02
    Added a badge for DeepWiki to the README to auto-refresh the wiki weekly
  • Issue comment#46coderabbitai[bot]2025-11-15 16:02
    Added a badge for DeepWiki to the README to auto-refresh the wiki weekly
  • Pull request#46richardodliu2025-11-15 16:01
  • Issue comment#43pprp2025-10-25 07:55
    [Bug] load config error
  • Issue#42github-actions[bot]2025-10-19 00:45
    [Bug] Initialization of A_log and dt_bias in GatedDeltaNet
  • Issue comment#39github-actions[bot]2025-10-19 00:45
    Support Finetuning?
  • Issue comment#35github-actions[bot]2025-09-28 00:43
    [Bug] Not recognized model type 'sba'
  • Issue comment#40github-actions[bot]2025-09-28 00:43
    [Bug] wrong python code alignment?
  • Issue#43chinoll2025-09-21 11:15
    [Bug] load config error
  • Issue comment#41yzhangcs2025-09-05 07:24
    [Bug] No attention_mask feed into the model when varlen=False
  • Issue comment#41alexxchen2025-09-05 06:49
    [Bug] No attention_mask feed into the model when varlen=False
  • Issue comment#41yzhangcs2025-09-05 06:35
    [Bug] No attention_mask feed into the model when varlen=False
  • Issue#41alexxchen2025-09-05 05:36
    [Bug] No attention_mask feed into the model when varlen=False
  • Issue comment#39EricZhang14122025-09-03 05:49
    Support Finetuning?
  • Issue comment#39yzhangcs2025-08-25 15:47
    Support Finetuning?
  • Issue#40hanlinxuy2025-08-23 01:19
    [Bug]

Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals β€” 224 stars here means stars gained during the window, not the repo's star count.