alibaba

alibaba / rtp-llm

#2
1,275235+3 todayCuda

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

📊 Project Info

Language
Cuda
Stars
1,275
Forks
235
Today
+3
Ranking
#2
Collection
Language
Trending Date
July 16, 2026
Last Push
7/16/2026

🏷️ Topics

gptinferencellamallmllm-servingllmopsmodel-serving

📸 Screenshots

rtp-llm screenshot 1