alibaba

alibaba / rtp-llm

#4
1,138197+3 todayCuda

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

📊 Project Info

Language
Cuda
Stars
1,138
Forks
197
Today
+3
Ranking
#4
Collection
Language
Trending Date
May 29, 2026
Last Push
5/29/2026

🏷️ Topics

gptinferencellamallmllm-servingllmopsmodel-serving

📸 Screenshots

rtp-llm screenshot 1