A vLLM out-of-tree platform plugin that enables running vLLM on NPU (Ascend/torch_npu).
最近更新: 14分钟前Omni_Infer is a suite of inference accelerators designed for the Ascend NPU platform, offering native support and an expanding feature set.
最近更新: 2天前Omni_Infer is a suite of inference accelerators designed for the Ascend NPU platform, offering native support and an expanding feature set.
最近更新: 1个月前
