alibaba

alibaba / rtp-llm

#1
1,154200+5 todayCuda

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

📊 Project Info

Language
Cuda
Stars
1,154
Forks
200
Today
+5
Ranking
#1
Collection
Language
Trending Date
June 1, 2026
Last Push
6/1/2026

🏷️ Topics

gptinferencellamallmllm-servingllmopsmodel-serving

📸 Screenshots

rtp-llm screenshot 1