Muon is Scalable for LLM Training
☆1,446Aug 3, 2025Updated 7 months ago
Alternatives and similar repositories for Moonlight
Users that are interested in Moonlight are comparing it to the libraries listed below
Sorting:
- MoBA: Mixture of Block Attention for Long-Context LLMs☆2,083Apr 3, 2025Updated 11 months ago
- Muon is an optimizer for hidden layers in neural networks☆2,398Jan 19, 2026Updated 2 months ago
- 🐳 Efficient Triton implementations for "Native Sparse Attention: Hardware-Aligned and Natively Trainable Sparse Attention"☆977Feb 5, 2026Updated last month
- A bidirectional pipeline parallelism algorithm for computation-communication overlap in DeepSeek V3/R1 training.☆2,934Jan 14, 2026Updated 2 months ago
- 🚀 Efficient implementations of state-of-the-art linear attention models☆4,630Updated this week
- FlashMLA: Efficient Multi-head Latent Attention Kernels☆12,521Feb 6, 2026Updated last month
- Flash-Muon: An Efficient Implementation of Muon Optimizer☆242Jun 15, 2025Updated 9 months ago
- ☆810Jun 9, 2025Updated 9 months ago
- Official Repo for Open-Reasoner-Zero☆2,086Jun 2, 2025Updated 9 months ago
- Analyze computation-communication overlap in V3/R1.☆1,149Mar 21, 2025Updated last year
- Kimi-VL: Mixture-of-Experts Vision-Language Model for Multimodal Reasoning, Long-Context Understanding, and Strong Agent Capabilities☆1,164Jul 15, 2025Updated 8 months ago
- verl: Volcano Engine Reinforcement Learning for LLMs☆19,919Updated this week
- Production-tested AI infrastructure tools for efficient AGI development and community-driven innovation☆7,972May 15, 2025Updated 10 months ago
- An Easy-to-use, Scalable and High-performance Agentic RL Framework based on Ray (PPO & DAPO & REINFORCE++ & TIS & vLLM & Ray & Async RL)☆9,191Updated this week
- Distributed Compiler based on Triton for Parallel Systems☆1,386Mar 11, 2026Updated last week
- DeepEP: an efficient expert-parallel communication library☆9,053Feb 9, 2026Updated last month
- A PyTorch native platform for training generative AI models☆5,162Updated this week
- FlashInfer: Kernel Library for LLM Serving☆5,145Updated this week
- Efficient Triton Kernels for LLM Training☆6,216Updated this week
- Expert Parallelism Load Balancer☆1,357Mar 24, 2025Updated 11 months ago
- SGLang is a high-performance serving framework for large language models and multimodal models.☆24,455Updated this week
- DeepGEMM: clean and efficient FP8 GEMM kernels with fine-grained scaling☆6,268Feb 27, 2026Updated 3 weeks ago
- Minimalistic large language model 3D-parallelism training☆2,617Feb 19, 2026Updated last month
- Technical report of Kimina-Prover Preview.☆363Jul 10, 2025Updated 8 months ago
- A Distributed Attention Towards Linear Scalability for Ultra-Long Context, Heterogeneous Data Training☆676Updated this week
- A fast communication-overlapping library for tensor/expert parallelism on GPUs.☆1,273Aug 28, 2025Updated 6 months ago
- The official repo of MiniMax-Text-01 and MiniMax-VL-01, large-language-model & vision-language-model based on Linear Attention☆3,362Jul 7, 2025Updated 8 months ago
- Mooncake is the serving platform for Kimi, a leading LLM service provided by Moonshot AI.☆4,921Mar 14, 2026Updated last week
- Democratizing Reinforcement Learning for LLMs☆5,259Updated this week
- Tile primitives for speedy kernels☆3,232Updated this week
- Ring attention implementation with flash attention☆996Sep 10, 2025Updated 6 months ago
- slime is an LLM post-training framework for RL Scaling.☆4,799Updated this week
- Meta Lingua: a lean, efficient, and easy-to-hack codebase to research LLMs.☆4,757Jul 18, 2025Updated 8 months ago
- Ongoing research training transformer models at scale☆15,744Updated this week
- Fast and memory-efficient exact attention☆22,832Updated this week
- [ICLR 2025 & COLM 2025] Official PyTorch implementation of the Forgetting Transformer and Adaptive Computation Pruning☆144Feb 25, 2026Updated 3 weeks ago
- NanoGPT (124M) in 2 minutes☆4,848Updated this week
- A library for accelerating Transformer models on NVIDIA GPUs, including using 8-bit and 4-bit floating point (FP8 and FP4) precision on H…☆3,211Updated this week
- Medusa: Simple Framework for Accelerating LLM Generation with Multiple Decoding Heads☆2,719Jun 25, 2024Updated last year