Muon is Scalable for LLM Training
☆1,546Aug 3, 2025Updated last year
Alternatives and similar repositories for Moonlight
Users that are interested in Moonlight are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- MoBA: Mixture of Block Attention for Long-Context LLMs☆2,191Apr 3, 2025Updated last year
- Muon is an optimizer for hidden layers in neural networks☆2,844May 24, 2026Updated 3 months ago
- 🐳 Efficient Triton implementations for "Native Sparse Attention: Hardware-Aligned and Natively Trainable Sparse Attention"☆1,021Feb 5, 2026Updated 7 months ago
- Flash-Muon: An Efficient Implementation of Muon Optimizer☆262Jun 15, 2025Updated last year
- A bidirectional pipeline parallelism algorithm for computation-communication overlap in DeepSeek V3/R1 training.☆3,010Jan 14, 2026Updated 8 months ago
- Wordpress hosting with auto-scaling - Free Trial Offer • AdFully Managed hosting for WordPress and WooCommerce businesses that need reliable, auto-scalable performance. Cloudways SafeUpdates now available.
- 🚀 Efficient implementations for emerging model architectures☆5,764Updated this week
- FlashMLA: Efficient Multi-head Latent Attention Kernels☆12,944Updated this week
- Kimi-VL: Mixture-of-Experts Vision-Language Model for Multimodal Reasoning, Long-Context Understanding, and Strong Agent Capabilities☆1,227Jul 15, 2025Updated last year
- ☆811Jun 9, 2025Updated last year
- Distributed Compiler and Optimized Parallel Kernels☆1,546Updated this week
- Official Repo for Open-Reasoner-Zero☆2,098Jun 2, 2025Updated last year
- Analyze computation-communication overlap in V3/R1.☆1,187Mar 21, 2025Updated last year
- A Distributed Attention Towards Linear Scalability for Ultra-Long Context, Heterogeneous Data Training☆943Updated this week
- VeOmni: Scaling Any Modality Model Training with Model-Centric Distributed Recipe Zoo☆2,215Updated this week
- Managed Kubernetes at scale on DigitalOcean • AdDigitalOcean Kubernetes includes the control plane, bandwidth allowance, container registry, automatic updates, and more for free.
- Production-tested AI infrastructure tools for efficient AGI development and community-driven innovation☆8,065May 15, 2025Updated last year
- DeepGEMM: clean and efficient BLAS kernel library on GPU☆7,845Updated this week
- Accelerating MoE with IO and Tile-aware Optimizations☆769Aug 29, 2026Updated 2 weeks ago
- DeepEP: an efficient expert-parallel communication library☆10,165Updated this week
- A PyTorch native platform for training generative AI models☆5,746Updated this week
- Efficient Triton Kernels for LLM Training☆6,618Updated this week
- NanoGPT (124M) in 90 seconds☆5,803Updated this week
- Expert Parallelism Load Balancer☆1,435Mar 24, 2025Updated last year
- slime is an LLM post-training framework for RL Scaling.☆8,499Updated this week
- AI Agents on DigitalOcean Gradient AI Platform • AdBuild production-ready AI agents using customizable tools or access multiple LLMs through a single endpoint. Create custom knowledge bases or connect external data.
- An Easy-to-use, Scalable and High-performance Agentic RL Framework based on Ray (PPO & DAPO & REINFORCE++ & VLM & TIS & vLLM & Ray & Asy…☆10,015Updated this week
- Minimalistic large language model 3D-parallelism training☆2,825Updated this week
- A fast communication-overlapping library for tensor/expert parallelism on GPUs.☆1,362Aug 28, 2025Updated last year
- verl/HybridFlow: A Flexible and Efficient RL Post-Training Framework☆23,487Updated this week
- ☆1,607Nov 17, 2025Updated 10 months ago
- Technical report of Kimina-Prover Preview.☆377Jul 10, 2025Updated last year
- Domain-specific language designed to streamline the development of high-performance GPU/CPU/Accelerators kernels☆7,431Updated this week
- The official repo of MiniMax-Text-01 and MiniMax-VL-01, large-language-model & vision-language-model based on Linear Attention☆3,468Jul 7, 2025Updated last year
- Democratizing Reinforcement Learning for LLMs☆5,828Updated this week
- AI Agents on DigitalOcean Gradient AI Platform • AdBuild production-ready AI agents using customizable tools or access multiple LLMs through a single endpoint. Create custom knowledge bases or connect external data.
- Ring attention implementation with flash attention☆1,057Sep 10, 2025Updated last year
- FlashInfer: Kernel Library for LLM Serving☆6,443Updated this week
- An efficient implementation of the NSA (Native Sparse Attention) kernel☆135Jun 24, 2025Updated last year
- A library for accelerating Transformer models on NVIDIA GPUs, including using 8-bit and 4-bit floating point (FP8 and FP4) precision on H…☆3,540Updated this week
- Meta Lingua: a lean, efficient, and easy-to-hack codebase to research LLMs.☆4,766Jul 18, 2025Updated last year
- Fast and memory-efficient exact attention☆24,966Updated this week
- 🔥 A minimal training framework for scaling FLA models☆416Apr 22, 2026Updated 4 months ago