bytedance / ByteTransformerLinks
optimized BERT transformer inference on NVIDIA GPU. https://arxiv.org/abs/2210.03052
☆478Updated last year
Alternatives and similar repositories for ByteTransformer
Users that are interested in ByteTransformer are comparing it to the libraries listed below
Sorting:
- ☆141Updated last year
- Transformer related optimization, including BERT, GPT☆59Updated 2 years ago
- ☆129Updated 9 months ago
- FlagGems is an operator library for large language models implemented in the Triton Language.☆690Updated this week
- ☆504Updated 3 weeks ago
- Running BERT without Padding☆475Updated 3 years ago
- A collection of memory efficient attention operators implemented in the Triton language.☆279Updated last year
- ☆150Updated 8 months ago
- BladeDISC is an end-to-end DynamIc Shape Compiler project for machine learning workloads.☆896Updated 9 months ago
- RTP-LLM: Alibaba's high-performance LLM inference engine for diverse applications.☆870Updated last week
- AI Accelerator Benchmark focuses on evaluating AI Accelerators from a practical production perspective, including the ease of use and ver…☆266Updated last month
- GLake: optimizing GPU memory management and IO transmission.☆480Updated 6 months ago
- A model compilation solution for various hardware☆450Updated last month
- ☆220Updated 2 years ago
- Zero Bubble Pipeline Parallelism☆428Updated 4 months ago
- Easy Parallel Library (EPL) is a general and efficient deep learning framework for distributed model training.☆268Updated 2 years ago
- Performance of the C++ interface of flash attention and flash attention v2 in large language model (LLM) inference scenarios.☆40Updated 7 months ago
- Microsoft Automatic Mixed Precision Library☆622Updated last year
- ☆139Updated last year
- ☆147Updated 7 months ago
- PyTorch distributed training acceleration framework☆53Updated last month
- ☆59Updated 10 months ago
- DeepLearning Framework Performance Profiling Toolkit☆290Updated 3 years ago
- A Easy-to-understand TensorOp Matmul Tutorial☆378Updated last year
- LiBai(李白): A Toolbox for Large-Scale Distributed Parallel Training☆408Updated 2 months ago
- DashInfer is a native LLM inference engine aiming to deliver industry-leading performance atop various hardware architectures, including …☆265Updated last month
- A simple high performance CUDA GEMM implementation.☆409Updated last year
- MegCC是一个运行时超轻量，高效，移植简单的深度学习模型编译器☆486Updated 11 months ago
- PyTorch bindings for CUTLASS grouped GEMM.☆152Updated last month
- export llama to onnx☆136Updated 9 months ago