chncwang / InsNetLinks
InsNet Runs Instance-dependent Neural Networks with Padding-free Dynamic Batching.
☆67Updated 3 years ago
Alternatives and similar repositories for InsNet
Users that are interested in InsNet are comparing it to the libraries listed below
Sorting:
- A Fast Muti-processing BERT-Inference System☆101Updated 3 years ago
- OneFlow models for benchmarking.☆104Updated last year
- Simple Dynamic Batching Inference☆145Updated 3 years ago
- Place for meetup slides☆140Updated 5 years ago
- pytorch源码阅读 0.2.0 版本☆91Updated 5 years ago
- oneflow documentation☆69Updated last year
- DeepLearning Framework Performance Profiling Toolkit☆292Updated 3 years ago
- Simple CuDNN wrapper☆30Updated 9 years ago
- Tutorials for writing high-performance GPU operators in AI frameworks.☆132Updated 2 years ago
- Models and examples built with OneFlow☆100Updated last year
- Running BERT without Padding☆475Updated 3 years ago
- Performance of the C++ interface of flash attention and flash attention v2 in large language model (LLM) inference scenarios.☆41Updated 8 months ago
- Transformer related optimization, including BERT, GPT☆59Updated 2 years ago
- Dynamic Tensor Rematerialization prototype (modified PyTorch) and simulator. Paper: https://arxiv.org/abs/2006.09616☆132Updated 2 years ago
- My learning notes about AI, including Machine Learning and Deep Learning.☆18Updated 6 years ago
- A small deep-learning framework with C++/Python/CUDA☆54Updated 7 years ago
- A simple deep learning framework that supports automatic differentiation and GPU acceleration.☆59Updated 2 years ago
- Inference framework for MoE layers based on TensorRT with Python binding☆41Updated 4 years ago
- ☆127Updated 4 years ago
- Compiler Infrastructure for Neural Networks☆147Updated 2 years ago
- tensorflow源码阅读笔记☆192Updated 7 years ago
- Tutorial code on how to build your own Deep Learning System in 2k Lines☆124Updated 8 years ago
- A super light-weight deep learning library based on NumPy in PyTorch fashion.☆94Updated 4 years ago
- implement bert in pure c++☆36Updated 5 years ago
- Distributed DataLoader For Pytorch Based On Ray☆24Updated 3 years ago
- Benchmark code for the "Online normalizer calculation for softmax" paper☆102Updated 7 years ago
- ☆12Updated 2 years ago
- optimized BERT transformer inference on NVIDIA GPU. https://arxiv.org/abs/2210.03052☆479Updated last year
- ☆98Updated 4 years ago
- ☆219Updated 2 years ago