qsyao / cudaBERT
A Fast Muti-processing BERT-Inference System
☆101Updated 2 years ago
Alternatives and similar repositories for cudaBERT:
Users that are interested in cudaBERT are comparing it to the libraries listed below
- InsNet Runs Instance-dependent Neural Networks with Padding-free Dynamic Batching.☆66Updated 3 years ago
- OneFlow models for benchmarking.☆104Updated 9 months ago
- pytorch源码阅读 0.2.0 版本☆90Updated 5 years ago
- A small deep-learning framework with C++/Python/CUDA☆53Updated 7 years ago
- oneflow documentation☆68Updated 10 months ago
- Simple Dynamic Batching Inference☆145Updated 3 years ago
- Place for meetup slides☆140Updated 4 years ago
- DeepLearning Framework Performance Profiling Toolkit☆284Updated 3 years ago
- ☆127Updated 3 years ago
- Tutorial code on how to build your own Deep Learning System in 2k Lines☆125Updated 8 years ago
- 动手学习TVM核心原理教程☆61Updated 4 years ago
- an automatic differentiation framework with dynamic graph/支持动态图的自动求导框架☆101Updated 5 years ago
- tensorflow源码阅读笔记☆190Updated 6 years ago
- TensorFlow code and pre-trained models for BERT☆24Updated 6 years ago
- Models and examples built with OneFlow☆97Updated 6 months ago
- ☆215Updated last year
- Fast implementation of BERT inference directly on NVIDIA (CUDA, CUBLAS) and Intel MKL☆545Updated 4 years ago
- Running BERT without Padding☆471Updated 3 years ago
- implement bert in pure c++☆36Updated 5 years ago
- AutodiffEngine☆13Updated 6 years ago
- A distributed logistic regression system based on ps-lite.☆45Updated 8 years ago
- ☆53Updated last year
- Dynamic Tensor Rematerialization prototype (modified PyTorch) and simulator. Paper: https://arxiv.org/abs/2006.09616☆132Updated last year
- ☆148Updated 4 months ago
- this is the release repository of superneurons☆52Updated 4 years ago
- C++ model train&inference framework☆224Updated 5 years ago
- A high-performance distributed deep learning system targeting large-scale and automated distributed training. If you have any interests, …☆111Updated last year
- A high-performance framework for training wide-and-deep recommender systems on heterogeneous cluster☆157Updated last year
- Easy Parallel Library (EPL) is a general and efficient deep learning framework for distributed model training.☆267Updated 2 years ago
- Performance of the C++ interface of flash attention and flash attention v2 in large language model (LLM) inference scenarios.☆36Updated 2 months ago