PaddlePaddle / PaddleCustomDevice
PaddlePaddle custom device implementaion. (『飞桨』自定义硬件接入实现)
☆80Updated this week
Alternatives and similar repositories for PaddleCustomDevice:
Users that are interested in PaddleCustomDevice are comparing it to the libraries listed below
- PaddlePaddle Developer Community☆97Updated this week
- Compiler Infrastructure for Neural Networks☆145Updated last year
- ☆142Updated last month
- ☆140Updated 9 months ago
- ☆78Updated 2 weeks ago
- ☆57Updated 3 months ago
- ☆247Updated last month
- 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☆474Updated 3 months ago
- A tutorial for CUDA&PyTorch☆126Updated last month
- ☆110Updated 11 months ago
- export llama to onnx☆112Updated last month
- ☆127Updated last month
- ☆35Updated 4 months ago
- A light llama-like llm inference framework based on the triton kernel.☆88Updated this week
- Serving Inside Pytorch☆154Updated this week
- learning how CUDA works☆200Updated 6 months ago
- ppl.cv is a high-performance image processing library of openPPL supporting various platforms.☆498Updated 3 months ago
- Paddle Automatically Diff Precision Toolkits.☆49Updated 10 months ago
- OneFlow->ONNX☆42Updated last year
- llm-export can export llm model to onnx.☆263Updated last month
- simplify >2GB large onnx model☆52Updated 2 months ago
- AI Accelerator Benchmark focuses on evaluating AI Accelerators from a practical production perspective, including the ease of use and ver…☆222Updated last week
- FlagScale is a large model toolkit based on open-sourced projects.☆223Updated this week
- Documentations for PaddlePaddle☆247Updated last week
- ☆33Updated last year
- ☆129Updated last month
- b站上的课程☆71Updated last year
- DeepLearning Framework Performance Profiling Toolkit☆283Updated 2 years ago
- FlagPerf is an open-source software platform for benchmarking AI chips.☆321Updated 2 weeks ago
- TensorRT encapsulation, learn, rewrite, practice.☆28Updated 2 years ago