MindSpore的vLLM插件，支持基于vLLM框架部署MindSpore模型的推理服务。
最近更新: 2个月前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: 5个月前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: 5个月前
