PaddlePaddle / Anakin
High performance Cross-platform Inference-engine, you could run Anakin on x86-cpu,arm, nv-gpu, amd-gpu,bitmain and cambricon devices.
☆531Updated 2 years ago
Alternatives and similar repositories for Anakin:
Users that are interested in Anakin are comparing it to the libraries listed below
- TVM integration into PyTorch☆453Updated 5 years ago
- heterogeneity-aware-lowering-and-optimization☆254Updated 11 months ago
- Quantized Neural Network PACKage - mobile-optimized implementation of quantized neural network operators☆1,533Updated 5 years ago
- FeatherCNN is a high performance inference engine for convolutional neural networks.☆1,215Updated 5 years ago
- To make it easy to benchmark AI accelerators☆182Updated 2 years ago
- BladeDISC is an end-to-end DynamIc Shape Compiler project for machine learning workloads.☆834Updated 2 weeks ago
- ☆127Updated 6 years ago
- A flexible and efficient deep neural network (DNN) compiler that generates high-performance executable from a DNN model description.☆972Updated 3 months ago
- Bolt is a deep learning library with high performance and heterogeneous flexibility.☆933Updated 5 months ago
- benchmark for embededded-ai deep learning inference engines, such as NCNN / TNN / MNN / TensorFlow Lite etc.☆204Updated 3 years ago
- ☆573Updated 6 years ago
- Place for meetup slides☆140Updated 4 years ago
- ☆208Updated 6 years ago
- Benchmarking Neural Network Inference on Mobile Devices☆365Updated last year
- Dive into Deep Learning Compiler☆646Updated 2 years ago
- A library for high performance deep learning inference on NVIDIA GPUs.☆550Updated 2 years ago
- Generate a quantization parameter file for ncnn framework int8 inference☆521Updated 4 years ago
- Minimal runtime core of Caffe, Forward only, GPU support and Memory efficiency.☆375Updated 4 years ago
- Mobile AI Compute Engine Model Zoo☆373Updated 3 years ago
- ppl.cv is a high-performance image processing library of openPPL supporting various platforms.☆495Updated 2 months ago
- Heterogeneous Run Time version of Caffe. Added heterogeneous capabilities to the Caffe, uses heterogeneous computing infrastructure frame…☆268Updated 6 years ago
- Optimizing Mobile Deep Learning on ARM GPU with TVM☆179Updated 6 years ago
- a c++/cuda template library for tensor lazy evaluation☆163Updated last year
- ☆125Updated 3 years ago
- tensorflow源码阅读笔记☆190Updated 6 years ago
- A common bricks library for building scalable and portable distributed machine learning.☆868Updated 7 months ago
- 面向产业应用的AI开源评测基准☆11Updated 2 years ago
- Winograd minimal convolution algorithm generator for convolutional neural networks.☆610Updated 4 years ago
- DeepLearning Framework Performance Profiling Toolkit☆281Updated 2 years ago