bytedance / effective_transformerLinks
Running BERT without Padding
☆476Updated 3 years ago
Alternatives and similar repositories for effective_transformer
Users that are interested in effective_transformer are comparing it to the libraries listed below
Sorting:
- optimized BERT transformer inference on NVIDIA GPU. https://arxiv.org/abs/2210.03052☆476Updated last year
- Transformer related optimization, including BERT, GPT☆59Updated 2 years ago
- ☆219Updated 2 years ago
- Easy Parallel Library (EPL) is a general and efficient deep learning framework for distributed model training.☆271Updated 2 years ago
- ☆413Updated 2 years ago
- Zero Bubble Pipeline Parallelism☆445Updated 8 months ago
- DeepLearning Framework Performance Profiling Toolkit☆294Updated 3 years ago
- Microsoft Automatic Mixed Precision Library☆634Updated last month
- LiBai(李白): A Toolbox for Large-Scale Distributed Parallel Training☆405Updated 5 months ago
- A collection of memory efficient attention operators implemented in the Triton language.☆287Updated last year
- OneFlow models for benchmarking.☆104Updated last year
- ☆130Updated last year
- PyTorch bindings for CUTLASS grouped GEMM.☆180Updated 3 weeks ago
- Simple Dynamic Batching Inference☆145Updated 3 years ago
- ☆141Updated last year
- Best practice for training LLaMA models in Megatron-LM☆664Updated 2 years ago
- Latency and Memory Analysis of Transformer Models for Training and Inference☆475Updated 8 months ago
- ☆123Updated last year
- A high-performance framework for training wide-and-deep recommender systems on heterogeneous cluster☆159Updated last year
- a fast and user-friendly runtime for transformer inference (Bert, Albert, GPT2, Decoders, etc) on CPU and GPU.☆1,536Updated 5 months ago
- Transformer related optimization, including BERT, GPT☆39Updated 2 years ago
- Fast implementation of BERT inference directly on NVIDIA (CUDA, CUBLAS) and Intel MKL☆545Updated 5 years ago
- BladeDISC is an end-to-end DynamIc Shape Compiler project for machine learning workloads.☆912Updated last year
- Easy and Efficient Transformer : Scalable Inference Solution For Large NLP model☆265Updated last year
- A Fast Muti-processing BERT-Inference System☆102Updated 3 years ago
- LLM training technologies developed by kwai☆69Updated last week
- Performance of the C++ interface of flash attention and flash attention v2 in large language model (LLM) inference scenarios.☆44Updated 10 months ago
- ☆22Updated 2 years ago
- Pipeline Parallelism for PyTorch☆783Updated last year
- The road to hack SysML and become an system expert☆506Updated last year