A vLLM out-of-tree platform plugin that enables running vLLM on NPU (Ascend/torch_npu).
最近更新: 38分钟前A vLLM out-of-tree platform plugin that enables running vLLM on NPU (Ascend/torch_npu).
最近更新: 1小时前A vLLM out-of-tree platform plugin that enables running vLLM on NPU (Ascend/torch_npu).
最近更新: 26天前A vLLM (0.12.0) out-of-tree platform plugin that enables running vLLM on NPU (Ascend/torch_npu).
最近更新: 2个月前A vLLM (0.12.0) out-of-tree platform plugin that enables running vLLM on NPU (Ascend/torch_npu).
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: 2个月前
