lucidrains / memory-efficient-attention-pytorchLinks
Implementation of a memory efficient multi-head attention as proposed in the paper, "Self-attention Does Not Need O(n²) Memory"
☆378Updated last year
Alternatives and similar repositories for memory-efficient-attention-pytorch
Users that are interested in memory-efficient-attention-pytorch are comparing it to the libraries listed below
Sorting:
- Implementation of Rotary Embeddings, from the Roformer paper, in Pytorch☆681Updated 6 months ago
- Implementation of fused cosine similarity attention in the same style as Flash Attention☆213Updated 2 years ago
- ☆290Updated 5 months ago
- Memory Efficient Attention (O(sqrt(n)) for Jax and PyTorch☆184Updated 2 years ago
- A simple way to keep track of an Exponential Moving Average (EMA) version of your Pytorch model☆590Updated 6 months ago
- An implementation of local windowed attention for language modeling☆450Updated 4 months ago
- Implementation of Linformer for Pytorch☆285Updated last year
- Implementation of ST-Moe, the latest incarnation of MoE after years of research at Brain, in Pytorch☆333Updated 11 months ago
- Transformer based on a variant of attention that is linear complexity in respect to sequence length☆768Updated last year
- Implementation of the conditionally routed attention in the CoLT5 architecture, in Pytorch☆228Updated 8 months ago
- Implementation of Flash Attention in Jax☆212Updated last year
- Annotated version of the Mamba paper☆482Updated last year
- Implementation of Mega, the Single-head Attention with Multi-headed EMA architecture that currently holds SOTA on Long Range Arena☆203Updated last year
- Code for the ALiBi method for transformer language models (ICLR 2022)☆530Updated last year
- Implementation of a Transformer, but completely in Triton☆265Updated 3 years ago
- Implementation of Block Recurrent Transformer - Pytorch☆217Updated 9 months ago
- FlashFFTConv: Efficient Convolutions for Long Sequences with Tensor Cores☆317Updated 5 months ago
- Helpful tools and examples for working with flex-attention☆811Updated this week
- Implementation of 💍 Ring Attention, from Liu et al. at Berkeley AI, in Pytorch☆514Updated 2 weeks ago
- Implementation of the Adan (ADAptive Nesterov momentum algorithm) Optimizer in Pytorch☆252Updated 2 years ago
- Experiments around a simple idea for inducing multiple hierarchical predictive model within a GPT☆213Updated 9 months ago
- Sequence modeling with Mega.☆295Updated 2 years ago
- Tutel MoE: Optimized Mixture-of-Experts Library, Support DeepSeek FP8/FP4☆829Updated this week
- Root Mean Square Layer Normalization☆241Updated 2 years ago
- Implementation of Recurrent Memory Transformer, Neurips 2022 paper, in Pytorch☆408Updated 4 months ago
- Implementation of Soft MoE, proposed by Brain's Vision team, in Pytorch☆294Updated 2 months ago
- Effortless plugin and play Optimizer to cut model training costs by 50%. New optimizer that is 2x faster than Adam on LLMs.☆380Updated last year
- Implementation of the Transformer variant proposed in "Transformer Quality in Linear Time"☆363Updated last year
- Code release for "Dropout Reduces Underfitting"☆313Updated 2 years ago
- Implementation of Bit Diffusion, Hinton's group's attempt at discrete denoising diffusion, in Pytorch☆346Updated last year