alibaba

alibaba / rtp-llm

#1
1,279238+2 todayCuda

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

📊 Project Info

Language
Cuda
Stars
1,279
Forks
238
Today
+2
Ranking
#1
Collection
Language
Trending Date
July 18, 2026
Last Push
7/18/2026

🏷️ Topics

gptinferencellamallmllm-servingllmopsmodel-serving

📸 Screenshots

rtp-llm screenshot 1