Skip to content

My take on batched Medusa: Simple Framework for Accelerating LLM Generation with Multiple Decoding Heads

Jupyter Notebook · active 2024-07-172026-04-20 (UTC)

Partial coverage14,861 / 18,136 hourly files (82%) · 2 absent upstream · 3,274 failed, retryable2024-07-172026-08-11 (UTC)— sampled evenly across the window, so rankings and trends hold; absolute counts scale up.
Events
447
Pushes
0
Pull requests
9
Issues
10
Stars
384
Forks
33

Activity over time

Daily event counts in the loaded window

Line chart, 643 days from 2024-07-17 to 2026-04-20. Pushes: 0 total, peak 0 in a day. Pull requests: 9 total, peak 2 in a day. Issues: 10 total, peak 1 in a day. Comments: 11 total, peak 2 in a day. Stars: 384 total, peak 12 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

Recent activity

Latest issues, pull requests and releases

  • Issue#139wittycheng2025-08-22 14:58
    loss value nan
  • Issue comment#95wittycheng2025-08-22 01:57
    Medusa Training Loss
  • Issue comment#134wittycheng2025-08-22 01:52
    why my train medusa head result is {'medusa0_top1': nan, 'medusa0_loss': nan, 'medusa1_top1': nan, 'medusa1_loss': nan, 'medusa2_top1': nan, 'medusa2_loss': nan, 'epoch': 0}
  • Issue comment#55PKUfreshman2025-07-27 07:29
    TypeError: __init__() got an unexpected keyword argument 'medusa_num_heads'
  • Issue#138Yi-Yu-Yvonne2025-07-25 20:30
    Support for Dynamic Cache?
  • Pull request#135JackCharlesZhang2025-04-14 00:37
  • Pull request#135JackCharlesZhang2025-04-14 00:37
  • Pull request#135JackCharlesZhang2025-04-13 23:37
  • Pull request#135JackCharlesZhang2025-04-13 23:36
  • Issue#134Mewo5182025-03-22 02:19
    why my train medusa head result is {'medusa0_top1': nan, 'medusa0_loss': nan, 'medusa1_top1': nan, 'medusa1_loss': nan, 'medusa2_top1': nan, 'medusa2_loss': nan, 'epoch': 0}
  • Pull request#131buvnswrn2024-12-28 01:32
  • Pull request#130alex43212024-12-15 04:10
  • Pull request#130alex43212024-12-15 04:10
  • Issue#126kimjoohyungsd2024-11-01 10:34
    About Code compatability
  • Issue comment#55YunSeoHwan2024-10-28 03:46
    TypeError: __init__() got an unexpected keyword argument 'medusa_num_heads'
  • Issue#125Achazwl2024-10-24 05:29
    Ask for data recipe to reproduce Medusa-2
  • Issue#124shrango2024-10-10 21:20
    [report bug] Encountered when inferencing with Mistral models
  • Issue comment#41chuangzhidan2024-09-29 08:28
    vLLM support
  • Issue comment#98huangzl192024-09-21 09:21
    ImportError: cannot import name 'is_flash_attn_available' from 'transformers.utils'
  • Issue comment#115xhjcxxl2024-09-14 03:01
    jinja2.exceptions.UndefinedError: dict object has no element 0
  • Issue#122PineTreeWss2024-09-13 11:47
    About the Tree Sparsity
  • Pull request#120simrathanspal2024-09-06 11:35
  • Pull request#120simrathanspal2024-09-06 11:20
  • Issue comment#119ByronHsu2024-08-26 05:22
    [Retraining] Use Liger Kernel to avoid multi-head logits materialization and scale the context length by N times
  • Issue#119ByronHsu2024-08-26 05:22
    [Retraining] Use Liger Kernel to avoid multi-head logits materialization and scale the context length by N times

Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 384 stars here means stars gained during the window, not the repo's star count.