xLLM-AI/xllm

A high-performance inference engine for LLM, VLM, DiT and REC models, optimized for diverse AI accelerators. It is hosted in OpenAtom Foundation.

语言：C++ · GitHub 星标：1,613 · Fork：325

话题：deepseek · glm · inference · inference-engine · large-language-models · llm-inference · qwen

在 GitHub 上查看原仓库