ascend 开源项目推荐（155 个）

Syllo /nvtop

AMD、Apple、Huawei、Intel、NVIDIA 和 Qualcomm 的 GPU 与加速器进程监控

gpustack /gpustack

用于高性能 AI 模型服务（vLLM、SGLang）以及按需、可通过 SSH 访问的 GPU 实例的 GPU 集群管理器。

Project-HAMi /HAMi

Kubernetes 上的异构 GPU 共享

data-infra /cube-studio

cubestudio开源云原生一站式机器学习/深度学习/大模型AI平台/MaaS/mlops/人工智能平台/训推平台，算法全链路流程，多租户，算力租赁平台，token中转，拖拉拽任务流pipeline编排，多机多卡分布式训练，超参搜索，推理服务，VGPU虚拟化，云边端协同，边缘计算，自动化标注平台，deepseek等大模型sft微调/奖励模型/强化学习训练，vllm/ollama/mindie大模型多机推理，私有知识库llmops智能体，AI模型市场，支持国产异构算力调度,昇腾/寒武纪/海光/摩尔/沐曦等，支持ib/roce/RDMA，信创支持

nndeploy /nndeploy

一款简单易用和高性能的AI部署框架 | An Easy-to-Use and High-Performance AI Deployment Framework

datawhalechina /torch-rechub

A Lighting Pytorch Framework for Recommendation Models, Easy-to-use and Easy-to-extend.

Ascend /pytorch

As the core component of the Huawei Ascend for PyTorch community, TorchNPU is a deep learning adapter plugin built by Ascend for PyTorch, enabling the PyTorch framework to directly invoke Ascend NPU and providing developers with the powerful compute capabilities of Ascend AI processors.

LSH9832 /edgeyolo

一个性能不错的边缘实时无锚点物体探测器

ModelEngine-Group /unified-cache-management

Persist and reuse KV Cache to speedup your LLM.

Krusty84 /triton-ascend-agent-dev-kit

A toolkit for AI agents used for development on Triton-Ascend for Ascend NPU

modelsphere /modelsphere

ModelSphere is an open-source LLM inference infrastructure designed to make production-grade model serving simple, efficient, and continuously optimized.

modelbox-ai /modelbox

A high performance, high expansion, easy to use framework for AI application. 为AI应用的开发者提供一套统一的高性能、易用的编程框架，快速基于AI全栈服务、开发跨端边云的AI行业应用，支持GPU，NPU加速。

youyve /nputop

An interactive Ascend-NPU process viewer

Ascend /triton-ascend

Triton adapter for Ascend. Mirror of https://gitcode.com/ascend/triton-ascend

GewelsJI /DGNet

Deep Gradient Network for Camouflaged Object Detection (MIR 2023). Our codebase supports PyTorch & Jittor & Huawei-Ascend platforms..

BreakingY /Media-Cognition-Pipeline

A general-purpose real-time streaming media and deep learning inference acceleration framework, supporting H264, H265, AAC, MP4, FLV, RTSP, RTMP, and YOLO.

zjunlp /ChineseHarm-bench

ChineseHarm-Bench: A Chinese Harmful Content Detection Benchmark

larpon /DeadAscend

A 2D point'n'click-like adventure game written in Qt/QML and Javascript

lvyufeng /PocketLLM

Inference engine for large language models on consumer GPUs, with deep optimization for older hardware

jackhanyuan /yolov5-ascend

YOLOv5 om model inference program on the Huawei Ascend platform