Pinned Loading

1. OptimAI-Lab/Minimalist_LLM_Pretraining OptimAI-Lab/Minimalist_LLM_Pretraining Public

   [ICML 2026] Memory-Efficient LLM Pretraining via Minimalist Optimizer Design

   Python 23

2. OptimAI-Lab/Memory_Efficient_Pretraining OptimAI-Lab/Memory_Efficient_Pretraining Public

   Scalable Parameter and Memory Efficient Pretraining for LLM: Recent Algorithmic Advances and Benchmarking

   Python 11 1

3. feather feather Public

   Feather is a module that enables effective sparsification of neural networks during training. This repository accompanies the paper "Feather: An Elegant Solution to Effective DNN Sparsification" (B…

   Python 12

4. OptimAI-Lab/large_lr_sgd OptimAI-Lab/large_lr_sgd Public

   Revisiting the Adam-SGD Gap in LLM Pre-Training: The Role of Large Effective Learning Rates

   Python 1