A vLLM (0.12.0) 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 expandin...

暂无描述

暂无描述

Omni-AI社区治理、运作、活动相关内容

Omni_Infer is a suite of inference accelerators designed for the Ascend NPU platform, offering native support and an expandin...