@cutty_flame
cutty_flame 暂无简介
A vLLM out-of-tree platform plugin that enables running vLLM on NPU (Ascend/torch_npu).
Omni_Infer is a suite of inference accelerators designed for the Ascend NPU platform, offering native support and an expanding feature set.
SGLang 是一个针对大语言模型和视觉语言模型的快速服务框架
