GitHub · Rust
pegainfer-project/pegainfer
Pure Rust + CUDA LLM inference engine — no PyTorch, OpenAI-compatible, serves Qwen3 to Kimi-K2
- Stars
- 748
- Forks
- 122
- Stars gained in 24 hours
- +3
- Forks gained in 24 hours
- +1
Topics: cuda, cuda-kernels, deepseek, gpu, inference, inference-engine, kimi, kimi-k2, kv-cache, llm
Latest data point: Nov 21, 2026 · 748 stars · 122 forks