knotgrass / attention
several types of attention modules written in PyTorch for learning purposes
☆44Updated 3 months ago
Alternatives and similar repositories for attention:
Users that are interested in attention are comparing it to the libraries listed below
- Official repository for the paper "SwitchHead: Accelerating Transformers with Mixture-of-Experts Attention"☆96Updated 4 months ago
- This repository contains papers for a comprehensive survey on accelerated generation techniques in Large Language Models (LLMs).☆12Updated 8 months ago
- ☆45Updated last year
- HGRN2: Gated Linear RNNs with State Expansion☆52Updated 5 months ago
- (Unofficial) PyTorch implementation of grouped-query attention (GQA) from "GQA: Training Generalized Multi-Query Transformer Models from …☆149Updated 8 months ago
- A repository for DenseSSMs☆86Updated 9 months ago
- Repository for Sparse Finetuning of LLMs via modified version of the MosaicML llmfoundry☆40Updated last year
- ☆38Updated 11 months ago
- Implementation of Griffin from the paper: "Griffin: Mixing Gated Linear Recurrences with Local Attention for Efficient Language Models"☆51Updated this week
- Inference Speed Benchmark for Learning to (Learn at Test Time): RNNs with Expressive Hidden States☆54Updated 6 months ago
- Pytorch Implementation of the sparse attention from the paper: "Generating Long Sequences with Sparse Transformers"☆69Updated this week
- Implementation of Infini-Transformer in Pytorch☆109Updated 3 weeks ago
- A simple but robust PyTorch implementation of RetNet from "Retentive Network: A Successor to Transformer for Large Language Models" (http…☆104Updated last year
- A single repo with all scripts and utils to train / fine-tune the Mamba model with or without FIM☆50Updated 9 months ago
- CUDA and Triton implementations of Flash Attention with SoftmaxN.☆67Updated 8 months ago
- Implementation of Agent Attention in Pytorch☆89Updated 6 months ago
- [ICLR 2024] This is the official PyTorch implementation of "QLLM: Accurate and Efficient Low-Bitwidth Quantization for Large Language Mod…☆22Updated 10 months ago
- Implementation of the paper: "Mixture-of-Depths: Dynamically allocating compute in transformer-based language models"☆79Updated this week
- [ICML 2024] When Linear Attention Meets Autoregressive Decoding: Towards More Effective and Efficient Linearized Large Language Models☆28Updated 7 months ago
- Implementation of IceFormer: Accelerated Inference with Long-Sequence Transformers on CPUs (ICLR 2024).☆22Updated 7 months ago
- A simple implementation of [Mamba: Linear-Time Sequence Modeling with Selective State Spaces](https://arxiv.org/abs/2312.00752)☆21Updated last year
- Contextual Position Encoding but with some custom CUDA Kernels https://arxiv.org/abs/2405.18719☆22Updated 7 months ago
- ☆15Updated 3 months ago
- Implementation of a modular, high-performance, and simplistic mamba for high-speed applications☆33Updated 2 months ago
- This is a simple torch implementation of the high performance Multi-Query Attention☆16Updated last year
- Explorations into the recently proposed Taylor Series Linear Attention☆92Updated 5 months ago
- Pytorch (Lightning) implementation of the Mamba model☆23Updated 9 months ago
- PyTorch implementation of Soft MoE by Google Brain in "From Sparse to Soft Mixtures of Experts" (https://arxiv.org/pdf/2308.00951.pdf)☆69Updated last year
- ☆29Updated 2 months ago