DeMo: Decoupled Momentum Optimization
☆202Dec 2, 2024Updated last year
Alternatives and similar repositories for DeMo
Users that are interested in DeMo are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Distributed Training Over-The-Internet☆1,069Oct 14, 2025Updated last year
- ☆23Jan 5, 2025Updated last year
- [Poster; ICLR 2026] [Oral; Neurips OPT2024] μLO: Compute-Efficient Meta-Generalization of Learned Optimizers☆16Apr 15, 2026Updated 7 months ago
- ☆69Mar 21, 2025Updated last year
- H-Net Dynamic Hierarchical Architecture☆81Sep 11, 2025Updated last year
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- ☆136Sep 29, 2026Updated last month
- Approximating the joint distribution of language models via MCTS☆22Nov 3, 2024Updated 2 years ago
- An experiment to see if chatgpt can improve the output of the stanford alpaca dataset☆12Mar 29, 2023Updated 3 years ago
- Entropy Based Sampling and Parallel CoT Decoding☆17Oct 9, 2024Updated 2 years ago
- Generates text with diffusion models. Reproduction of the Continous Diffusion for Categorical Data paper by Deepmind☆20Dec 9, 2024Updated last year
- MoE training for Me and You and maybe other people☆400Mar 15, 2026Updated 8 months ago
- smolLM with Entropix sampler on pytorch☆148Oct 31, 2024Updated 2 years ago
- Flash-Muon: An Efficient Implementation of Muon Optimizer☆265Jun 15, 2025Updated last year
- Train a SmolLM-style llm on fineweb-edu in JAX/Flax with an assortment of optimizers.☆19Jul 24, 2025Updated last year
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- working implimention of deepseek MLA☆45Jan 8, 2025Updated last year
- Stick-breaking attention☆64Jul 1, 2025Updated last year
- Scaling is a distributed training library and installable dependency designed to scale up neural networks, with a dedicated module for tr…☆66Nov 18, 2025Updated last year
- an open source reproduction of NVIDIA's nGPT (Normalized Transformer with Representation Learning on the Hypersphere)☆112Mar 7, 2025Updated last year
- ☆27Jul 9, 2024Updated 2 years ago
- ☆72Sep 11, 2026Updated 2 months ago
- ☆36Mar 12, 2025Updated last year
- Code for Adam-mini: Use Fewer Learning Rates To Gain More https://arxiv.org/abs/2406.16793☆463May 13, 2025Updated last year
- OpenDiLoCo: An Open-Source Framework for Globally Distributed Low-Communication Training☆609Jul 17, 2026Updated 4 months ago
- Serverless GPU API endpoints on Runpod - Get Bonus Credits • AdSkip the infrastructure headaches. Auto-scaling, pay-as-you-go, no-ops approach lets you focus on innovating your application.
- Demonstration that finetuning RoPE model on larger sequences than the pre-trained model adapts the model context limit☆62Jun 21, 2023Updated 3 years ago
- Code for NeurIPS 2024 Spotlight: "Scaling Laws and Compute-Optimal Training Beyond Fixed Training Durations"☆94Oct 30, 2024Updated 2 years ago
- PCCL (Prime Collective Communications Library) implements fault tolerant collective communications over IP☆165Sep 12, 2025Updated last year
- Simple Transformer in Jax☆143Jun 22, 2024Updated 2 years ago
- Asynchronous P2P communication backend for decentralized pipeline parallelism☆54Jul 28, 2026Updated 3 months ago
- [ICLR 2025 & COLM 2025] Official PyTorch implementation of the Forgetting Transformer and Adaptive Computation Pruning☆155Feb 25, 2026Updated 8 months ago
- [ICLR 2026] When it comes to optimizers, it's always better to be safe than sorry☆421Sep 26, 2025Updated last year
- minimal Energy-based transformer☆43Dec 11, 2025Updated 11 months ago
- Tiny re-implementation of MDM in style of LLaDA and nano-gpt speedrun☆56Mar 10, 2025Updated last year
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- NSA Triton Kernels written with GPT5 and Opus 4.1☆71Aug 12, 2025Updated last year
- ☆623Sep 11, 2026Updated 2 months ago
- ☆37Oct 4, 2026Updated last month
- Agent-assisted hyperparameter optimization 📈☆20Aug 2, 2026Updated 3 months ago
- research impl of Native Sparse Attention (2502.11089)☆63Feb 19, 2025Updated last year
- Entropy Based Sampling and Parallel CoT Decoding☆3,433Nov 13, 2024Updated 2 years ago
- Positional Skip-wise Training for Efficient Context Window Extension of LLMs to Extremely Length (ICLR 2024)☆208May 20, 2024Updated 2 years ago
Are these results useful?