alibaba

alibaba / rtp-llm

#16
1,267231Cuda

RTP-LLM: Alibaba's high-performance LLM inference engine for diverse applications.

📊 Project Info

Language
Cuda
Stars
1,267
Forks
231
Ranking
#16
Collection
Language
Trending Date
July 12, 2026
Last Push
7/12/2026

🏷️ Topics

gptinferencellamallmllm-servingllmopsmodel-serving

📸 Screenshots

rtp-llm screenshot 1