jd-opensource

jd-opensource / xllm

#11
1,317219+1 todayC++

A high-performance inference engine for LLM, VLM, DiT and REC models, optimized for diverse AI accelerators.

📊 Project Info

Language
C++
Stars
1,317
Forks
219
Today
+1
Ranking
#11
Collection
Language
Trending Date
June 3, 2026
Last Push
6/3/2026

🏷️ Topics

deepseekglminferenceinference-enginelarge-language-modelsllm-inferenceqwen

📸 Screenshots

xllm screenshot 1xllm screenshot 2xllm screenshot 3