ArtificialZeng / baichuan-speedup

纯c++的全平台llm加速库,支持python调用,支持baichuan, glm, llama, moss基座,手机端流畅运行chatglm-6B级模型单卡可达10000+token / s,
45Updated last year

Related projects

Alternatives and complementary repositories for baichuan-speedup