Watch omniai/omni-npu

A vLLM (0.12.0) out-of-tree platform plugin that enables running vLLM on NPU (Ascend/torch_npu).

Watch omniai/omni-eplb

Watch moran/omni-npu forked from omniai/omni-npu

A vLLM (0.12.0) out-of-tree platform plugin that enables running vLLM on NPU (Ascend/torch_npu).

Watch omniai/omni-proxy

Watch Eric Cai/omni_infer forked from omniai/omni_infer

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

Watch MindSpore/vllm-mindspore

关闭

MindSpore的vLLM插件，支持基于vLLM框架部署MindSpore模型的推理服务。

Watch MindSpore/ms_custom_ops

关闭

MindSpore 自定义算子扩展（ms_custom_ops），是依托 MindSpore 原生的自定义算子与自定义 pass 能力构建而成的独立算子扩展插件包。

Watch MindSpore/mindspore

关闭

GVP

MindSpore is a new open source deep learning training/inference framework that could be used for mobile, edge and cloud scenarios.

Watch TronZhang/omni_infer_tron forked from omniai/omni_infer

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

Watch MindSpore/akg

关闭

AKG(Auto Kernel Generator) is an optimizer for operators in Deep Learning Networks, which provides the ability to automatically fuse ops with specific patterns.