shreyansh26 / Attention-Mask-PatternsLinks
Using FlexAttention to compute attention with different masking patterns
β43Updated 8 months ago
Alternatives and similar repositories for Attention-Mask-Patterns
Users that are interested in Attention-Mask-Patterns are comparing it to the libraries listed below
Sorting:
- DPO, but faster πβ42Updated 5 months ago
- This repo is based on https://github.com/jiaweizzhao/GaLoreβ28Updated 8 months ago
- Here we will test various linear attention designs.β58Updated last year
- Official repository of paper "RNNs Are Not Transformers (Yet): The Key Bottleneck on In-context Retrieval"β27Updated last year
- The official repository for SkyLadder: Better and Faster Pretraining via Context Window Schedulingβ32Updated 2 months ago
- β45Updated 3 months ago
- Triton Implementation of HyperAttention Algorithmβ48Updated last year
- GoldFinch and other hybrid transformer componentsβ45Updated 10 months ago
- β34Updated 11 months ago
- β79Updated 9 months ago
- The source code of our work "Prepacking: A Simple Method for Fast Prefilling and Increased Throughput in Large Language Models" [AISTATS β¦β59Updated 7 months ago
- β31Updated last year
- β54Updated 10 months ago
- Official repository for the paper "Approximating Two-Layer Feedforward Networks for Efficient Transformers"β37Updated last year
- β20Updated last year
- Official implementation of "The Sparse Frontier: Sparse Attention Trade-offs in Transformer LLMs"β32Updated last month
- Flash-Muon: An Efficient Implementation of Muon Optimizerβ115Updated this week
- FlexAttention w/ FlashAttention3 Supportβ26Updated 7 months ago
- The simplest implementation of recent Sparse Attention patterns for efficient LLM inference.β62Updated 4 months ago
- β51Updated last year
- A repository for research on medium sized language models.β76Updated last year
- Utilities for Training Very Large Modelsβ58Updated 8 months ago
- β53Updated this week
- Simple and efficient pytorch-native transformer training and inference (batched)β75Updated last year
- β31Updated last year
- Cascade Speculative Draftingβ29Updated last year
- Implementation of the paper: "Leave No Context Behind: Efficient Infinite Context Transformers with Infini-attention" from Google in pyTOβ¦β55Updated last month
- Implementation of Hyena Hierarchy in JAXβ10Updated 2 years ago
- Repository for Sparse Finetuning of LLMs via modified version of the MosaicML llmfoundryβ42Updated last year
- Make triton easierβ47Updated 11 months ago