Pure Rust + CUDA LLM inference engine — no PyTorch, OpenAI-compatible, serves Qwen3 to Kimi-K2
- inference
- kimi
- llm-serving
- model-serving
140,194 visible repositories in the index
1–2 of 2 · Most stars
Pure Rust + CUDA LLM inference engine — no PyTorch, OpenAI-compatible, serves Qwen3 to Kimi-K2
Aggregates images taken this week, from previous years and presents them on a web page with a simple slideshow.