qsyao / cudaBERTLinks
A Fast Muti-processing BERT-Inference System
☆102Updated 3 years ago
Alternatives and similar repositories for cudaBERT
Users that are interested in cudaBERT are comparing it to the libraries listed below
Sorting:
- OneFlow models for benchmarking.☆104Updated last year
- InsNet Runs Instance-dependent Neural Networks with Padding-free Dynamic Batching.☆67Updated 4 years ago
- DeepLearning Framework Performance Profiling Toolkit☆296Updated 3 years ago
- Fast implementation of BERT inference directly on NVIDIA (CUDA, CUBLAS) and Intel MKL☆547Updated 5 years ago
- Running BERT without Padding☆478Updated 3 years ago
- C++ model train&inference framework☆223Updated 6 years ago
- Place for meetup slides☆140Updated 5 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
- Simple Dynamic Batching Inference☆145Updated 3 years ago
- ☆219Updated 2 years ago
- pytorch源码阅读 0.2.0 版本☆91Updated 6 years ago
- oneflow documentation☆69Updated last year
- A small deep-learning framework with C++/Python/CUDA☆54Updated 7 years ago
- Tutorial code on how to build your own Deep Learning System in 2k Lines☆123Updated 8 years ago
- My solutions to the assignments of dlsys course (CSE599G1: Deep Learning System Spring 2017)☆10Updated 8 years ago
- (Spring 2018) Assignment 2: Graph Executor with TVM☆124Updated 7 years ago
- Models and examples built with OneFlow☆101Updated last year
- Transformer related optimization, including BERT, GPT☆59Updated 2 years ago
- AutodiffEngine☆13Updated 6 years ago
- Analyze TensorFlow source code☆19Updated 8 years ago
- PyTorch On Angel, arming PyTorch with a powerful Parameter Server, which enable PyTorch to train very big models.☆169Updated 3 months ago
- Vector Search Engine base on BRPC + FAISS☆151Updated 6 years ago
- saving memory by recomputing for keras☆37Updated 5 years ago
- implement bert in pure c++☆36Updated 5 years ago
- CS294; AI For Systems and Systems For AI☆227Updated 6 years ago
- Inference framework for MoE layers based on TensorRT with Python binding☆41Updated 4 years ago
- LAMB Optimizer for Large Batch Training (TensorFlow version)☆121Updated 6 years ago
- Easy Parallel Library (EPL) is a general and efficient deep learning framework for distributed model training.☆271Updated 2 years ago
- A distributed logistic regression system based on ps-lite.☆45Updated 8 years ago
- FastNN provides distributed training examples that use EPL.☆85Updated 3 years ago