tobna / TaylorShiftLinks
This repository contains the code for the paper "TaylorShift: Shifting the Complexity of Self-Attention from Squared to Linear (and Back) using Taylor-Softmax"
☆10Updated 4 months ago
Alternatives and similar repositories for TaylorShift
Users that are interested in TaylorShift are comparing it to the libraries listed below
Sorting:
- A repository for DenseSSMs☆88Updated last year
- Implementation of a modular, high-performance, and simplistic mamba for high-speed applications☆36Updated 9 months ago
- Implementation of Agent Attention in Pytorch☆91Updated last year
- Some personal experiments around routing tokens to different autoregressive attention, akin to mixture-of-experts☆120Updated 9 months ago
- This is a simple torch implementation of the high performance Multi-Query Attention☆16Updated last year
- RWKV is an RNN with transformer-level LLM performance. It can be directly trained like a GPT (parallelizable). So it's combining the best…☆51Updated 5 months ago
- Explorations into adversarial losses on top of autoregressive loss for language modeling☆37Updated 5 months ago
- Implementation of Infini-Transformer in Pytorch☆111Updated 7 months ago
- Implementation of MoE Mamba from the paper: "MoE-Mamba: Efficient Selective State Space Models with Mixture of Experts" in Pytorch and Ze…☆110Updated this week
- Implementation of a Light Recurrent Unit in Pytorch☆48Updated 10 months ago
- Pytorch Implementation of the paper: "Learning to (Learn at Test Time): RNNs with Expressive Hidden States"☆25Updated 3 weeks ago
- ☆47Updated last year
- HGRN2: Gated Linear RNNs with State Expansion☆55Updated 11 months ago
- User-friendly implementation of the Mixture-of-Sparse-Attention (MoSA). MoSA selects distinct tokens for each head with expert choice rou…☆23Updated 3 months ago
- MambaFormer in-context learning experiments and implementation for https://arxiv.org/abs/2402.04248☆55Updated last year
- ☆182Updated 10 months ago
- A simple but robust PyTorch implementation of RetNet from "Retentive Network: A Successor to Transformer for Large Language Models" (http…☆105Updated last year
- ☆34Updated 5 months ago
- Here we will test various linear attention designs.☆62Updated last year
- Autoregressive Image Generation☆32Updated 2 months ago
- ☆48Updated 6 months ago
- [ICLR 2025 & COLM 2025] Official PyTorch implementation of the Forgetting Transformer and Adaptive Computation Pruning☆122Updated this week
- Implementation of Griffin from the paper: "Griffin: Mixing Gated Linear Recurrences with Local Attention for Efficient Language Models"☆56Updated 3 weeks ago
- [ICML 2024] When Linear Attention Meets Autoregressive Decoding: Towards More Effective and Efficient Linearized Large Language Models☆33Updated last year
- The this is the official implementation of "DAPE: Data-Adaptive Positional Encoding for Length Extrapolation"☆39Updated 10 months ago
- ☆16Updated 2 years ago
- Implementation of the proposed DeepCrossAttention by Heddes et al at Google research, in Pytorch☆91Updated 5 months ago
- PyTorch implementation of moe, which stands for mixture of experts☆46Updated 4 years ago
- Self contained pytorch implementation of a sinkhorn based router, for mixture of experts or otherwise☆37Updated 11 months ago
- 32 times longer context window than vanilla Transformers and up to 4 times longer than memory efficient Transformers.☆48Updated 2 years ago