#attention (27 Repositories)
Ranked open-source repositories tagged with #attention, scored by pull request acceptance likelihood and maintainer engagement velocity.
27.8%
74.0h
27 repositories tagged #attention
flashinfer-ai/flashinfer
FlashInfer: Kernel Library for LLM Serving
NVIDIA/cudnn-frontend
cuDNN Frontend is NVIDIA's modern, open-source entry point to the cuDNN library and a growing collection of high-performance open-source kernels.
feichai0017/loom-infer
Rust-native GPU operator library for LLM inference, built with cuda-oxide
flagos-ai/FlagAttention
A collection of memory efficient attention operators implemented in the Triton language.
feichai0017/orbitkv
High Performance KV Cache for LLM Inference
google-research/scenic
Scenic: A Jax Library for Computer Vision Research and Beyond
feichai0017/oxide-infer
Rust-native GPU operator library for LLM inference, built with cuda-oxide
harleyszhang/lite_llama
A light llama-like llm inference framework based on the triton kernel.
jmaczan/tiny-vllm
Build your own high performance LLM inference engine in C++ and CUDA - a smaller version of vLLM
feichai0017/loom-kernels
Rust-first high-performance CUDA operator library for LLM inference
lucidrains/dreamer4
Implementation of Danijar's latest iteration for his Dreamer line of work
harleyszhang/rapid_llm
RapidLLM is an LLM inference framework with continuous batching, tensor and data parallelism, quantized weights, and with pluggable Triton/CUDA kernels.
graykode/nlp-tutorial
Natural Language Processing Tutorial for Deep Learning Researchers
wushilian/CRNN_Attention_OCR_Chinese
CRNN with attention to do OCR,add Chinese recognition
DongjunLee/transformer-tensorflow
TensorFlow implementation of 'Attention Is All You Need (2017. 6)'
kaushalshetty/Structured-Self-Attention
A Structured Self-attentive Sentence Embedding
AnubhavGupta3377/Text-Classification-Models-Pytorch
Implementation of State-of-the-art Text Classification Models in Pytorch
Gsunshine/Enjoy-Hamburger
[ICLR 2021 top 3%] Is Attention Better Than Matrix Decomposition?
cbaziotis/neat-vision
Neat (Neural Attention) Vision, is a visualization tool for the attention mechanisms of deep-learning models for Natural Language Processing (NLP) tasks. (framework-agnostic)
HadoopIt/rnn-nlu
A TensorFlow implementation of Recurrent Neural Networks for Sequence Classification and Sequence Labeling
hyunwoongko/transformer
Transformer: PyTorch Implementation of "Attention Is All You Need"
chengchingwen/Transformers.jl
Julia Implementation of Transformer models
jadore801120/attention-is-all-you-need-pytorch
A PyTorch implementation of the Transformer model in "Attention is All You Need".
MorvanZhou/NLP-Tutorials
Simple implementations of NLP models. Tutorials are written in Chinese on my website https://mofanpy.com
mit-han-lab/spatten
[HPCA'21] SpAtten: Efficient Sparse Attention Architecture with Cascade Token and Head Pruning
szagoruyko/attention-transfer
Improving Convolutional Networks via Attention Transfer (ICLR 2017)
km1994/nlp_paper_study
该仓库主要记录 NLP 算法工程师相关的顶会论文研读笔记