NUS-HPC-AI-Lab / pytorch-lamb
PyTorch implementation of LAMB for ImageNet/ResNet-50 training
☆14Updated 3 years ago
Related projects ⓘ
Alternatives and complementary repositories for pytorch-lamb
- Accuracy 77%. Large batch deep learning optimizer LARS for ImageNet with PyTorch and ResNet, using Horovod for distribution. Optional acc…☆38Updated 3 years ago
- Code for "Training Neural Networks with Fixed Sparse Masks" (NeurIPS 2021).☆56Updated 2 years ago
- The implementation for MLSys 2023 paper: "Cuttlefish: Low-rank Model Training without All The Tuning"☆43Updated last year
- ☆35Updated 3 years ago
- Code for the paper: Why Transformers Need Adam: A Hessian Perspective☆40Updated 6 months ago
- Code for Sanity-Checking Pruning Methods: Random Tickets can Win the Jackpot☆43Updated 4 years ago
- Revisiting Efficient Training Algorithms For Transformer-based Language Models (NeurIPS 2023)☆79Updated last year
- This package implements THOR: Transformer with Stochastic Experts.☆61Updated 3 years ago
- [ICML 2024] Junk DNA Hypothesis: A Task-Centric Angle of LLM Pre-trained Weights through Sparsity; Lu Yin*, Ajay Jaiswal*, Shiwei Liu, So…☆15Updated 5 months ago
- Parameter Efficient Transfer Learning with Diff Pruning☆72Updated 3 years ago
- Repository of the paper "Accelerating Transformer Inference for Translation via Parallel Decoding"☆108Updated 7 months ago
- Patch convolution to avoid large GPU memory usage of Conv2D☆79Updated 5 months ago
- ☆39Updated 3 years ago
- ☆192Updated last year
- A fusion of a linear layer and a cross entropy loss, written for pytorch in triton.☆54Updated 3 months ago
- Triton-based implementation of Sparse Mixture of Experts.☆184Updated last month
- Activation-aware Singular Value Decomposition for Compressing Large Language Models☆49Updated 2 weeks ago
- [ICLR 2023] "Sparsity May Cry: Let Us Fail (Current) Sparse Neural Networks Together!" Shiwei Liu, Tianlong Chen, Zhenyu Zhang, Xuxi Chen…☆27Updated last year
- PyTorch repository for ICLR 2022 paper (GSAM) which improves generalization (e.g. +3.8% top-1 accuracy on ImageNet with ViT-B/32)☆138Updated 2 years ago
- ☆46Updated last year
- Official Pytorch Implementation of Our Paper Accepted at ICLR 2024-- Dynamic Sparse No Training: Training-Free Fine-tuning for Sparse LLM…☆35Updated 7 months ago
- Preprint: Asymmetry in Low-Rank Adapters of Foundation Models☆29Updated 8 months ago
- [ICLR 2024 Spotlight] Code for the paper "Merge, Then Compress: Demystify Efficient SMoE with Hints from Its Routing Policy"☆64Updated 5 months ago
- Block Sparse movement pruning☆78Updated 3 years ago
- Why Do We Need Weight Decay in Modern Deep Learning? [NeurIPS 2024]☆49Updated last month
- Code accompanying the NeurIPS 2020 paper: WoodFisher (Singh & Alistarh, 2020)☆46Updated 3 years ago
- Official repository for LightSeq: Sequence Level Parallelism for Distributed Training of Long Context Transformers☆196Updated 2 months ago
- Code associated with the paper **Fine-tuning Language Models over Slow Networks using Activation Compression with Guarantees**.☆25Updated last year
- ☆59Updated 3 years ago
- ☆132Updated last year