KellerJordan / Muon
Muon optimizer: +>30% sample efficiency with <3% wallclock overhead
β575Updated 3 weeks ago
Alternatives and similar repositories for Muon:
Users that are interested in Muon are comparing it to the libraries listed below
- [ICLR2025 Spotlightπ₯] Official Implementation of TokenFormer: Rethinking Transformer Scaling with Tokenized Model Parametersβ548Updated 2 months ago
- Helpful tools and examples for working with flex-attentionβ726Updated last week
- Implementation of the sparse attention pattern proposed by the Deepseek team in their "Native Sparse Attention" paperβ593Updated 3 weeks ago
- Code for Adam-mini: Use Fewer Learning Rates To Gain More https://arxiv.org/abs/2406.16793β405Updated last week
- Quick implementation of nGPT, learning entirely on the hypersphere, from NvidiaAIβ279Updated last month
- Muon is Scalable for LLM Trainingβ1,022Updated 3 weeks ago
- Implementation of π Ring Attention, from Liu et al. at Berkeley AI, in Pytorchβ511Updated 5 months ago
- β419Updated this week
- π³ Efficient Triton implementations for "Native Sparse Attention: Hardware-Aligned and Natively Trainable Sparse Attention"β631Updated last month
- Memory layers use a trainable key-value lookup mechanism to add extra parameters to a model without increasing FLOPs. Conceptually, sparsβ¦β317Updated 4 months ago
- Normalized Transformer (nGPT)β168Updated 5 months ago
- When it comes to optimizers, it's always better to be safe than sorryβ217Updated 3 weeks ago
- A subset of PyTorch's neural network modules, written in Python using OpenAI's Triton.β530Updated this week
- Pretraining code for a large-scale depth-recurrent language modelβ743Updated last week
- Block Diffusion: Interpolating Between Autoregressive and Diffusion Language Modelsβ536Updated last week
- β264Updated 2 months ago
- Minimalistic 4D-parallelism distributed training framework for education purposeβ991Updated last month
- πΎ OAT: A research-friendly framework for LLM online alignment, including preference learning, reinforcement learning, etc.β325Updated this week
- Ring attention implementation with flash attentionβ737Updated 2 weeks ago
- The official implementation of Tensor ProducT ATTenTion Transformer (T6)β361Updated this week
- Repo for "LoLCATs: On Low-Rank Linearizing of Large Language Models"β230Updated 2 months ago
- β166Updated 2 months ago
- Large Context Attentionβ704Updated 2 months ago
- π Efficiently (pre)training foundation models with native PyTorch features, including FSDP for training and SDPA implementation of Flashβ¦β240Updated this week
- Official JAX implementation of Learning to (Learn at Test Time): RNNs with Expressive Hidden Statesβ405Updated 8 months ago
- Dream 7B, a large diffusion language modelβ551Updated last week
- Understanding R1-Zero-Like Training: A Critical Perspectiveβ863Updated last week
- [ICML 2024] CLLMs: Consistency Large Language Modelsβ391Updated 5 months ago
- β176Updated 4 months ago
- Efficient LLM Inference over Long Sequencesβ368Updated this week