C++ · Apache-2.0
jmaczan/tiny-vllm
Build your own high performance LLM inference engine in C++ and CUDA - a smaller version of vLLM
★ 1.2k
Stars
102 forks · 0 open issues
+1.3/day
Growth · measured
Stars counted between two of our own snapshots roughly a week apart. The repository page gives the exact span.
30.5
Momentum / 100
see the breakdown below
9mo ago
Created
last push 6d ago
Star history
How this score was built
| Component | Weight | Earned | Why |
|---|---|---|---|
| Velocity | 55 | 6.9 | +1.3/day, log-scaled against a 750/day ceiling |
| Acceleration | 15 | 0.0 | last week ran 0.98× the monthly pace |
| Freshness | 15 | 14.7 | last push 6d ago; decays to zero at 180 days |
| Scale | 15 | 8.9 | 1.2k stars, log-scaled against 150k — stops a 3-star repo topping the board |
| Momentum | 100 | 30.5 | sum of the above |
Detail
| Topics | aiattentionbatchingcoursecppcudahpcinferencellmllm-inferencepagedattentiontiny-vllmvllm |
| Matched on | LLM & Inference (llm-inference) |
| Short window | +9 stars over 7 days = 1.3/day |
| Long window | +34 stars over 26 days = 1.3/day |
| Lifetime average | 4.40 stars/day over 269 days |
| First seen here | 2026-10-11 |
| Last read | 2d ago |