Pinned Loading

1. jd-opensource/xllm jd-opensource/xllm Public

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

   C++ 1.4k 242

2. xllm xllm Public

   Forked from jd-opensource/xllm

   A high-performance inference engine for LLMs, optimized for diverse AI accelerators.

   C++