Python · Apache-2.0
vllm-project/vllm
A high-throughput and memory-efficient inference and serving engine for LLMs
★ 96.4k
Stars
24.4k forks · 9.9k open issues
+78/day
Growth · measured
Stars counted between two of our own snapshots roughly a week apart. The repository page gives the exact span.
65.8
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 | 36.3 | +78/day, log-scaled against a 750/day ceiling |
| Acceleration | 15 | 0.0 | last week ran 0.72× the monthly pace |
| Freshness | 15 | 15.0 | last push 2d ago; decays to zero at 180 days |
| Scale | 15 | 14.4 | 96.4k stars, log-scaled against 150k — stops a 3-star repo topping the board |
| Momentum | 100 | 65.8 | sum of the above |
Detail
| Topics | amdblackwellcudadeepseekdeepseek-v3gptgpt-ossinferencekimillamallmllm-servingmodel-servingmoeopenaipytorchqwenqwen3tputransformer |
| Matched on | LLM & Inference (llm, llm-serving) |
| Short window | +549 stars over 7 days = 78.4/day |
| Long window | +2.8k stars over 26 days = 109.3/day |
| Lifetime average | 70.61 stars/day over 1,365 days |
| First seen here | 2026-10-11 |
| Last read | 2d ago |