PaddlePaddle / PaddleCustomDevice
PaddlePaddle custom device implementaion. (『飞桨』自定义硬件接入实现)
☆71Updated this week
Related projects ⓘ
Alternatives and complementary repositories for PaddleCustomDevice
- PaddlePaddle Developer Community☆88Updated this week
- ☆242Updated last week
- Compiler Infrastructure for Neural Networks☆143Updated last year
- Serving Inside Pytorch☆145Updated this week
- ☆138Updated 2 weeks ago
- ☆140Updated 7 months ago
- Efficient operation implementation based on the Cambricon Machine Learning Unit (MLU) .☆103Updated this week
- ☆124Updated 2 weeks ago
- MegCC是一个运行时超轻量，高效，移植简单的深度学习模型编译器☆473Updated last month
- ☆232Updated 2 years ago
- ☆77Updated last week
- learning how CUDA works☆169Updated 3 months ago
- b站上的课程☆70Updated last year
- ppl.cv is a high-performance image processing library of openPPL supporting various platforms.☆494Updated 3 weeks ago
- ☆100Updated 8 months ago
- ☆26Updated last year
- ☆32Updated last month
- ☆57Updated this week
- llm-export can export llm model to onnx.☆231Updated last week
- DeepSparkHub selects hundreds of application algorithms and models, covering various fields of AI and general-purpose computing, to suppo…☆57Updated this week
- run ChatGLM2-6B in BM1684X☆48Updated 8 months ago
- export llama to onnx☆98Updated 5 months ago
- CNStream is a streaming framework for building Cambricon machine learning pipelines http://forum.cambricon.com https://gitee.com/Solu…☆46Updated last year
- ☆70Updated last year
- A large number of cuda/tensorrt cases . 大量案例来学习cuda/tensorrt☆108Updated 2 years ago
- TensorRT Plugin Autogen Tool☆366Updated last year
- nndeploy是一款模型端到端部署框架。以多端推理以及基于有向无环图模型部署为基础，致力为用户提供跨平台、简单易用、高性能的模型部署体验。☆636Updated this week
- AI Accelerator Benchmark focuses on evaluating AI Accelerators from a practical production perspective, including the ease of use and ver…☆206Updated this week
- Compare multiple optimization methods on triton to imporve model service performance☆46Updated 10 months ago
- Documentations for PaddlePaddle☆245Updated this week