Cuda · Apache-2.0
flashinfer-ai/flashinfer
FlashInfer: Kernel Library for LLM Serving
★ 6.9k
Stars
1.7k forks · 1.4k open issues
+6.1/day
Growth · measured
Stars counted between two of our own snapshots roughly a week apart. The repository page gives the exact span.
42.5
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 | 16.3 | +6.1/day, log-scaled against a 750/day ceiling |
| Acceleration | 15 | 0.0 | last week ran 0.59× the monthly pace |
| Freshness | 15 | 15.0 | last push 2d ago; decays to zero at 180 days |
| Scale | 15 | 11.1 | 6.9k stars, log-scaled against 150k — stops a 3-star repo topping the board |
| Momentum | 100 | 42.5 | sum of the above |
Detail
| Topics | attentioncudadistributed-inferencegpujitlarge-large-modelsllm-inferencemoenvidiapytorch |
| Matched on | LLM & Inference (llm-inference) |
| Short window | +43 stars over 7 days = 6.1/day |
| Long window | +272 stars over 26 days = 10.5/day |
| Lifetime average | 5.70 stars/day over 1,202 days |
| First seen here | 2026-10-11 |
| Last read | 2d ago |