alibaba

alibaba / rtp-llm

#4
1,170204+16 todayCuda

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

📊 Project Info

Language
Cuda
Stars
1,170
Forks
204
Today
+16
Ranking
#4
Collection
Language
Trending Date
June 2, 2026
Last Push
6/2/2026

🏷️ Topics

gptinferencellamallmllm-servingllmopsmodel-serving

📸 Screenshots

rtp-llm screenshot 1