Tencent / TurboTransformers
a fast and user-friendly runtime for transformer inference (Bert, Albert, GPT2, Decoders, etc) on CPU and GPU.
☆1,466Updated last year
Related projects: ⓘ
- LightSeq: A High Performance Library for Sequence Processing and Generation☆3,169Updated last year
- Fast implementation of BERT inference directly on NVIDIA (CUDA, CUBLAS) and Intel MKL☆522Updated 3 years ago
- Running BERT without Padding☆455Updated 2 years ago
- Pretrained language model and its related optimization techniques developed by Huawei Noah's Ark Lab.☆3,016Updated 7 months ago
- Efficient, scalable and enterprise-grade CPU/GPU inference server for 🤗 Hugging Face transformer models 🚀☆1,643Updated 10 months ago
- Boosting your Web Services of Deep Learning Applications.☆1,230Updated 3 years ago
- FastFormers - highly efficient transformer models for NLU☆700Updated 8 months ago
- HugeCTR is a high efficiency GPU framework designed for Click-Through-Rate (CTR) estimating training☆933Updated 2 weeks ago
- A PyTorch-based knowledge distillation toolkit for natural language processing☆1,586Updated last year
- Bagua Speeds up PyTorch☆872Updated last month
- EasyTransfer is designed to make the development of transfer learning in NLP applications easier.☆852Updated 2 years ago
- Ongoing research training transformer language models at scale, including: BERT & GPT-2☆1,314Updated 5 months ago
- A fast MoE impl for PyTorch☆1,520Updated 2 months ago
- Ongoing research training transformer language models at scale, including: BERT & GPT-2☆1,830Updated 2 weeks ago
- Bolt is a deep learning library with high performance and heterogeneous flexibility.☆909Updated last month
- PyTorch extensions for high performance and large scale training.☆3,149Updated 2 weeks ago
- ELECTRA: Pre-training Text Encoders as Discriminators Rather Than Generators☆2,321Updated 5 months ago
- Repository for the paper "Optimal Subarchitecture Extraction for BERT"☆469Updated 2 years ago
- Transformer related optimization, including BERT, GPT☆5,773Updated 5 months ago
- BladeDISC is an end-to-end DynamIc Shape Compiler project for machine learning workloads.☆796Updated 3 weeks ago
- FB (Facebook) + GEMM (General Matrix-Matrix Multiplication) - https://code.fb.com/ml-applications/fbgemm/☆1,169Updated this week
- A library for accelerating Transformer models on NVIDIA GPUs, including using 8-bit floating point (FP8) precision on Hopper and Ada GPUs…☆1,811Updated this week
- PatrickStar enables Larger, Faster, Greener Pretrained Models for NLP and democratizes AI for everyone.☆747Updated last year
- Mesh TensorFlow: Model Parallelism Made Easier☆1,581Updated 10 months ago
- [DEPRECATED] Repo for exploring multi-task learning approaches to learning sentence representations☆757Updated 3 years ago
- A flexible and efficient deep neural network (DNN) compiler that generates high-performance executable from a DNN model description.☆952Updated this week
- optimized BERT transformer inference on NVIDIA GPU. https://arxiv.org/abs/2210.03052☆451Updated 6 months ago
- An efficient implementation of the popular sequence models for text generation, summarization, and translation tasks. https://arxiv.org/p…☆432Updated 2 years ago
- FlexFlow Serve: Low-Latency, High-Performance LLM Serving☆1,645Updated this week
- High performance distributed framework for training deep learning recommendation models based on PyTorch.☆394Updated this week