Skip to content

🌸 Run LLMs at home, BitTorrent-style. Fine-tuning and inference up to 10x faster than offloading. This fork includes a token system to prioritize requests from peers.

active 2023-10-022026-08-11 (UTC)

Partial coverage19,461 / 25,093 hourly files (78%) · 2 absent upstream · 5,629 failed, retryable2023-10-022026-08-12 (UTC)— sampled evenly across the window, so rankings and trends hold; absolute counts scale up.
Events
2K
Pushes
56
Pull requests
39
Issues
42
Stars
1.6K
Forks
171

Activity over time

Daily event counts in the loaded window

Line chart, 1045 days from 2023-10-02 to 2026-08-11. Pushes: 56 total, peak 7 in a day. Pull requests: 39 total, peak 5 in a day. Issues: 42 total, peak 3 in a day. Comments: 66 total, peak 7 in a day. Stars: 1,568 total, peak 19 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 comment#226ravi1504952026-02-26 04:31
    [Feature Request] Direct server-server communication ("and then" clause)
  • Issue comment#626jtzl2025-08-17 16:21
    Updating tutorial
  • Pull request#626jtzl2025-08-17 16:20
  • Pull request#623kyoungbinkim2025-07-21 23:17
  • Pull request#623kyoungbinkim2025-05-08 02:40
  • Issue comment#483echeloni112025-05-01 22:45
    How can we make this work long term?
  • Issue comment#549SeekPoint2025-04-29 04:08
    Error when trying to launch private swarm using locally stored model
  • Issue comment#622bulutthecat2025-03-05 02:09
    Vulkan compute backend support?
  • Issue#622bulutthecat2025-03-05 01:54
    Vulkan compute backend support?
  • Issue#621blazgocompany2025-02-13 00:04
    Private Petals Swarm with different networks?
  • Issue#620hsoftxl2025-01-06 07:04
    does anyone run success on mac?
  • Issue#618hsoftxl2025-01-06 04:03
    run llama failed (Apple M2 Ultra)
  • Pull request#619jhancock19752025-01-01 18:40
  • Issue comment#618hsoftxl2024-12-31 06:33
    run llama failed (Apple M2 Ultra)
  • Issue#618hsoftxl2024-12-30 03:56
    run llama failed
  • Issue#617adnanbaqi2024-12-08 10:50
    After, the latest update the health monitor is no longer working , nor in flask neither in docker
  • Issue comment#562adnanbaqi2024-12-07 23:05
    Reachability issue while connecting to private swarm
  • Issue#616asmit2032024-11-02 06:57
    Feature Request - Support For VLM's
  • Issue#616asmit2032024-11-02 04:52
    Support For VLM's
  • Issue#615valentimarco2024-10-27 19:04
    Create a bash script for the docker image
  • Issue comment#609xloem2024-10-19 22:48
    Error using the local llama3.1 model
  • Issue comment#614magejosh2024-09-29 07:46
    Performance improving chances in the future
  • Issue#614oldcpple2024-09-27 02:31
    Performance improving chances in the future
  • Issue#613andrew-morris-rgs2024-09-12 00:40
    Mac M3 Llama-3.1-405B crashing
  • Pull request#612mandlinsarah2024-09-04 06:21

Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 1,568 stars here means stars gained during the window, not the repo's star count.