lumia431/photon_infer

A High-Performance LLM Inference Engine with vLLM-Style Continuous Batching

⭐ 119 ⑂ 7 C++ MIT · 2026-01-03推送

ai-infra inference-engine llm-inference modern-cpp vllm continuous-batching paged-attention

119

Watchers

0

贡献者

0

Commits

0

Releases

1

Open Issues

2026-01-03

最近推送

原文中文

暂无 README