Python
NVIDIA/TensorRT-LLM
TensorRT LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and supports state-of-the-art optimizations to perform inference efficiently on NVIDIA GPUs. TensorRT LLM also contains components to create Python and C++ runtimes that orchestrate the inference execution in a performant way.
★ 15k
Stars
2.9k forks · 1.9k open issues
+6.9/day
Growth · measured
Stars counted between two of our own snapshots roughly a week apart. The repository page gives the exact span.
44.2
Momentum / 100
see the breakdown below
3y ago
Created
last push 2d ago
Star history
How this score was built
| Component | Weight | Earned | Why |
|---|---|---|---|
| Velocity | 55 | 17.1 | +6.9/day, log-scaled against a 750/day ceiling |
| Acceleration | 15 | 0.0 | last week ran 0.78× the monthly pace |
| Freshness | 15 | 15.0 | last push 2d ago; decays to zero at 180 days |
| Scale | 15 | 12.1 | 15k stars, log-scaled against 150k — stops a 3-star repo topping the board |
| Momentum | 100 | 44.2 | sum of the above |
Detail
| Topics | blackwellcudallm-servingmoepytorch |
| Matched on | LLM & Inference (llm-serving) |
| Short window | +48 stars over 7 days = 6.9/day |
| Long window | +228 stars over 26 days = 8.8/day |
| Lifetime average | 12.76 stars/day over 1,177 days |
| First seen here | 2026-10-11 |
| Last read | 2d ago |