selfsupervised-ai / Natural-GaLore
An extention to the GaLore paper, to perform Natural Gradient Descent in low rank subspace
☆16Updated 6 months ago
Alternatives and similar repositories for Natural-GaLore
Users that are interested in Natural-GaLore are comparing it to the libraries listed below
Sorting:
- Work in progress.☆62Updated last month
- The source code of our work "Prepacking: A Simple Method for Fast Prefilling and Increased Throughput in Large Language Models" [AISTATS …☆59Updated 7 months ago
- Repository for Sparse Finetuning of LLMs via modified version of the MosaicML llmfoundry☆41Updated last year
- This repository contains code for the MicroAdam paper.☆18Updated 5 months ago
- ☆51Updated 6 months ago
- From GaLore to WeLore: How Low-Rank Weights Non-uniformly Emerge from Low-Rank Gradients. Ajay Jaiswal, Lu Yin, Zhenyu Zhang, Shiwei Liu,…☆47Updated 3 weeks ago
- Official implementation of "The Sparse Frontier: Sparse Attention Trade-offs in Transformer LLMs"☆27Updated 3 weeks ago
- Beyond KV Caching: Shared Attention for Efficient LLMs☆19Updated 9 months ago
- ☆78Updated 8 months ago
- This repo is based on https://github.com/jiaweizzhao/GaLore☆27Updated 7 months ago
- Code for studying the super weight in LLM☆100Updated 5 months ago
- Tree Attention: Topology-aware Decoding for Long-Context Attention on GPU clusters☆126Updated 5 months ago
- ☆13Updated this week
- ☆12Updated 4 months ago
- The simplest implementation of recent Sparse Attention patterns for efficient LLM inference.☆60Updated 3 months ago
- The official repository for SkyLadder: Better and Faster Pretraining via Context Window Scheduling☆29Updated last month
- ☆25Updated 6 months ago
- Implementation for the paper: CMoE: Fast Carving of Mixture-of-Experts for Efficient LLM Inference☆19Updated 2 months ago
- Transformers components but in Triton☆33Updated this week
- The official implementation of the paper "Towards Efficient Mixture of Experts: A Holistic Study of Compression Techniques (TMLR)".☆67Updated last month
- Activation-aware Singular Value Decomposition for Compressing Large Language Models☆66Updated 6 months ago
- Official implementation of the ICML 2024 paper RoSA (Robust Adaptation)☆41Updated last year
- ☆81Updated last year
- Accelerate LLM preference tuning via prefix sharing with a single line of code☆41Updated 2 weeks ago
- Flash-Muon: An Efficient Implementation of Muon Optimizer☆103Updated last week
- Triton Implementation of HyperAttention Algorithm☆48Updated last year
- Using FlexAttention to compute attention with different masking patterns☆43Updated 7 months ago
- ☆68Updated 10 months ago
- ☆78Updated 4 months ago
- Mask-Enhanced Autoregressive Prediction: Pay Less Attention to Learn More☆31Updated this week