C++ · Apache-2.0
zhihu/ZhiLight
A highly optimized LLM inference acceleration engine for Llama and its variants.
★ 906
Stars
105 forks · 6 open issues
−1.0/wk
Growth · measured
Stars counted between two of our own snapshots roughly a week apart. The repository page gives the exact span.
8.6
Momentum / 100
see the breakdown below
23mo ago
Created
last push 7mo ago
Star history
How this score was built
| Component | Weight | Earned | Why |
|---|---|---|---|
| Velocity | 55 | 0.0 | −1.0/wk, log-scaled against a 750/day ceiling |
| Acceleration | 15 | 0.0 | needs 7-day and 30-day rates side by side |
| Freshness | 15 | 0.0 | last push 7mo ago; decays to zero at 180 days |
| Scale | 15 | 8.6 | 906 stars, log-scaled against 150k — stops a 3-star repo topping the board |
| Momentum | 100 | 8.6 | sum of the above |
Detail
| Topics | cudadeepseek-r1gptinference-enginellamallmllm-inferencellm-servingmodel-servingpytorch |
| Matched on | LLM & Inference (llm-inference, llm-serving) |
| Short window | +-1 stars over 7 days = -0.1/day |
| Long window | +-2 stars over 26 days = -0.1/day |
| Lifetime average | 1.30 stars/day over 699 days |
| First seen here | 2026-10-11 |
| Last read | 2d ago |