Python
NVIDIA/Megatron-LM
Ongoing research training transformer models at scale
★ 18.3k
Stars
4.7k forks · 2k open issues
+5.6/day
Growth · measured
Stars counted between two of our own snapshots roughly a week apart. The repository page gives the exact span.
43.0
Momentum / 100
see the breakdown below
7y ago
Created
last push 2d ago
Star history
How this score was built
| Component | Weight | Earned | Why |
|---|---|---|---|
| Velocity | 55 | 15.6 | +5.6/day, log-scaled against a 750/day ceiling |
| Acceleration | 15 | 0.0 | last week ran 0.66× the monthly pace |
| Freshness | 15 | 15.0 | last push 2d ago; decays to zero at 180 days |
| Scale | 15 | 12.4 | 18.3k stars, log-scaled against 150k — stops a 3-star repo topping the board |
| Momentum | 100 | 43.0 | sum of the above |
Detail
| Topics | large-language-modelsmodel-paratransformers |
| Matched on | LLM & Inference (large-language-models) |
| Short window | +39 stars over 7 days = 5.6/day |
| Long window | +220 stars over 26 days = 8.5/day |
| Lifetime average | 6.58 stars/day over 2,786 days |
| First seen here | 2026-10-11 |
| Last read | 2d ago |