Python · MIT
bigscience-workshop/petals
🌸 Run LLMs at home, BitTorrent-style. Fine-tuning and inference up to 10x faster than offloading
★ 10.7k
Stars
655 forks · 114 open issues
+3.3/day
Growth · measured
Stars counted between two of our own snapshots roughly a week apart. The repository page gives the exact span.
25.0
Momentum / 100
see the breakdown below
4y ago
Created
last push 2y ago
Star history
How this score was built
| Component | Weight | Earned | Why |
|---|---|---|---|
| Velocity | 55 | 12.1 | +3.3/day, log-scaled against a 750/day ceiling |
| Acceleration | 15 | 1.2 | last week ran 1.08× the monthly pace |
| Freshness | 15 | 0.0 | last push 2y ago; decays to zero at 180 days |
| Scale | 15 | 11.7 | 10.7k stars, log-scaled against 150k — stops a 3-star repo topping the board |
| Momentum | 100 | 25.0 | sum of the above |
Detail
| Topics | bloomchatbotdeep-learningdistributed-systemsfalcongptguanacolanguage-modelslarge-language-modelsllamamachine-learningmixtralneural-networksnlppipeline-parallelismpretrained-modelspytorchtensor-parallelismtransformervolunteer-computing |
| Matched on | LLM & Inference (large-language-models) |
| Short window | +23 stars over 7 days = 3.3/day |
| Long window | +79 stars over 26 days = 3.0/day |
| Lifetime average | 6.65 stars/day over 1,608 days |
| First seen here | 2026-10-11 |
| Last read | 2d ago |