FasterTransformer
Transformer component
A high-performance transformer-based NLP component optimized for GPU acceleration and integration into various frameworks.
Transformer related optimization, including BERT, GPT
6k stars
62 watching
893 forks
Language: C++
last commit: 8 months ago
Linked from 1 awesome list
bertgptpytorchtransformer
hannibal046/awesome-llmRelated projects:
| Repository | Description | Stars |
|---|---|---|
 opennmt/ctranslate2 | A high-performance library for efficient inference with Transformer models on CPUs and GPUs. | 3,404 |
| nvidia/tensorrt | A high-performance deep learning inference platform on NVIDIA GPUs | 10,807 |
 google-research/text-to-text-transfer-transformer | Provides tools and libraries for training and fine-tuning large language models using transformer architectures | 6,170 |
 kimiyoung/transformer-xl | Implementations of a neural network architecture for language modeling | 3,611 |
| nvidia/megatron-lm | A research framework for training large language models at scale using GPU optimized techniques. | 10,562 |
 codertimo/bert-pytorch | An implementation of Google's 2018 BERT model in PyTorch, allowing pre-training and fine-tuning for natural language processing tasks | 6,222 |
| nvidia/minkowskiengine | An auto-differentiation library for sparse tensors used in computer vision and deep learning applications. | 2,485 |
 facebookresearch/metaseq | A codebase for working with Open Pre-trained Transformers, enabling deployment and fine-tuning of transformer models on various platforms. | 6,515 |
 eleutherai/gpt-neox | Provides a framework for training large-scale language models on GPUs with advanced features and optimizations. | 6,941 |
 tensorspeech/tensorflowtts | Real-time speech synthesis using state-of-the-art architectures | 3,839 |
| google-research/bert | Provides pre-trained models and code for natural language processing tasks using TensorFlow | 38,204 |
| google-research/vision_transformer | Provides pre-trained models and code for training vision transformers and mixers using JAX/Flax | 10,450 |
 luolc/adabound | An optimizer that combines the benefits of Adam and SGD algorithms | 2,907 |
 tensorpack/tensorpack | A high-performance neural network training interface for TensorFlow that focuses on speed and flexibility. | 6,303 |
 brightmart/roberta_zh | Implements RoBERTa for Chinese pre-training using TensorFlow and provides PyTorch versions for loading and training | 2,618 |