facebookresearch / schedule_freeLinks
Schedule-Free Optimization in PyTorch
☆2,190Updated 2 months ago
Alternatives and similar repositories for schedule_free
Users that are interested in schedule_free are comparing it to the libraries listed below
Sorting:
- PyTorch compiler that accelerates training and inference. Get built-in optimizations for performance, memory, parallelism, and easily wri…☆1,380Updated this week
- Official repository for our work on micro-budget training of large-scale diffusion models.☆1,499Updated 6 months ago
- A JAX research toolkit for building, editing, and visualizing neural networks.☆1,804Updated last month
- Muon is an optimizer for hidden layers in neural networks☆1,218Updated last week
- Tensors, for human consumption☆1,270Updated last month
- PyTorch native quantization and sparsity for training and inference☆2,191Updated this week
- For optimization algorithm research and development.☆522Updated this week
- Minimalistic 4D-parallelism distributed training framework for education purpose☆1,598Updated 2 weeks ago
- TensorDict is a pytorch dedicated tensor container.☆942Updated last week
- NanoGPT (124M) in 3 minutes☆2,851Updated this week
- UNet diffusion model in pure CUDA☆610Updated last year
- A minimal PyTorch implementation of probabilistic diffusion models for 2D datasets.☆919Updated last year
- A PyTorch native platform for training generative AI models☆4,056Updated this week
- Helpful tools and examples for working with flex-attention☆887Updated this week
- 🦁 Lion, new optimizer discovered by Google Brain using genetic algorithms that is purportedly better than Adam(w), in Pytorch☆2,144Updated 7 months ago
- Puzzles for learning Triton☆1,769Updated 8 months ago
- Annotated version of the Mamba paper☆486Updated last year
- Train to 94% on CIFAR-10 in <6.3 seconds on a single A100. Or ~95.79% in ~110 seconds (or less!)☆1,271Updated 7 months ago
- Tile primitives for speedy kernels☆2,523Updated last week
- 🚀 Efficient implementations of state-of-the-art linear attention models☆2,928Updated this week
- maximal update parametrization (µP)☆1,558Updated last year
- Official Implementation of "ADOPT: Modified Adam Can Converge with Any β2 with the Optimal Rate"☆426Updated 7 months ago
- Type annotations and runtime checking for shape and dtype of JAX/NumPy/PyTorch/etc. arrays. https://docs.kidger.site/jaxtyping/☆1,482Updated 2 months ago
- What would you do with 1000 H100s...☆1,064Updated last year
- The official implementation of “Sophia: A Scalable Stochastic Second-order Optimizer for Language Model Pre-training”☆964Updated last year
- Code for BLT research paper☆1,740Updated 2 months ago
- nanoGPT style version of Llama 3.1☆1,397Updated 11 months ago
- 4M: Massively Multimodal Masked Modeling☆1,750Updated last month
- [ICLR 2025] Samba: Simple Hybrid State Space Models for Efficient Unlimited Context Language Modeling☆894Updated 2 months ago
- Official repository for the paper "Grokfast: Accelerated Grokking by Amplifying Slow Gradients"☆556Updated last year