MoBA: Mixture of Block Attention for Long-Context LLMs
β2,199Apr 3, 2025Updated last year
Alternatives and similar repositories for MoBA
Users that are interested in MoBA are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Muon is Scalable for LLM Trainingβ1,562Aug 3, 2025Updated last year
- π³ Efficient Triton implementations for "Native Sparse Attention: Hardware-Aligned and Natively Trainable Sparse Attention"β1,029Feb 5, 2026Updated 9 months ago
- π Efficient implementations for emerging model architecturesβ6,059Updated this week
- β255Nov 19, 2025Updated 11 months ago
- [NeurIPS'24 Spotlight, ICLR'25, ICML'25] To speed up Long-context LLMs' inference, approximate and dynamic sparse calculate the attentionβ¦β1,231Updated this week
- Deploy to Railway using AI coding agents - Free Credits Offer β’ AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- FlashMLA: Efficient Multi-head Latent Attention Kernelsβ13,278Oct 27, 2026Updated 3 weeks ago
- Kimi-VL: Mixture-of-Experts Vision-Language Model for Multimodal Reasoning, Long-Context Understanding, and Strong Agent Capabilitiesβ1,228Jul 15, 2025Updated last year
- Implementation of the sparse attention pattern proposed by the Deepseek team in their "Native Sparse Attention" paperβ817Aug 15, 2025Updated last year
- The official repo of MiniMax-Text-01 and MiniMax-VL-01, large-language-model & vision-language-model based on Linear Attentionβ3,475Jul 7, 2025Updated last year
- A Distributed Attention Towards Linear Scalability for Ultra-Long Context, Heterogeneous Data Trainingβ974Updated this week
- β1,634Nov 17, 2025Updated last year
- β812Jun 9, 2025Updated last year
- Official Repo for Open-Reasoner-Zeroβ2,102Jun 2, 2025Updated last year
- A bidirectional pipeline parallelism algorithm for computation-communication overlap in DeepSeek V3/R1 training.β3,035Jan 14, 2026Updated 10 months ago
- End-to-end encrypted cloud storage - Proton Drive β’ AdSpecial offer: 40% Off Yearly / 80% Off First Month. Protect your most important files, photos, and documents from prying eyes.
- DeepEP: an efficient expert-parallel communication libraryβ10,450Oct 21, 2026Updated 3 weeks ago
- [ICLR 2025] DuoAttention: Efficient Long-Context LLM Inference with Retrieval and Streaming Headsβ545Feb 10, 2025Updated last year
- verl/HybridFlow: A Flexible and Efficient RL Post-Training Frameworkβ24,266Updated this week
- Fast and memory-efficient exact attentionβ25,316Updated this week
- Mooncake is the serving platform for Kimi, a leading LLM service provided by Moonshot AI.β7,061Updated this week
- Production-tested AI infrastructure tools for efficient AGI development and community-driven innovationβ8,140May 15, 2025Updated last year
- A sparse attention kernel supporting mix sparse patternsβ566Jan 18, 2026Updated 10 months ago
- Distributed Compiler and Optimized Parallel Kernelsβ1,580Sep 18, 2026Updated 2 months ago
- Ring attention implementation with flash attentionβ1,069Sep 10, 2025Updated last year
- GPU virtual machines on DigitalOcean Gradient AI β’ AdGet to production fast with high-performance AMD and NVIDIA GPUs you can spin up in seconds. The definition of operational simplicity.
- β3,465Mar 7, 2025Updated last year
- VeOmni: Scaling Any Modality Model Training with Model-Centric Distributed Recipe Zooβ2,296Updated this week
- SeerAttention: Learning Intrinsic Sparse Attention in Your LLMsβ224Jul 10, 2026Updated 4 months ago
- FlashInfer: Kernel Library for LLM Servingβ6,958Updated this week
- DeepGEMM: clean and efficient BLAS kernel library on GPUβ9,204Oct 20, 2026Updated 3 weeks ago
- Ongoing research training transformer models at scaleβ18,433Updated this week
- Helpful tools and examples for working with flex-attentionβ1,267Updated this week
- A fast communication-overlapping library for tensor/expert parallelism on GPUs.β1,379Aug 28, 2025Updated last year
- Expert Parallelism Load Balancerβ1,478Mar 24, 2025Updated last year
- Managed Kubernetes at scale on DigitalOcean β’ AdDigitalOcean Kubernetes includes the control plane, bandwidth allowance, container registry, automatic updates, and more for free.
- [ICML2025] SpargeAttention: A training-free sparse attention that accelerates any model inference.β1,268Feb 25, 2026Updated 8 months ago
- [ICML 2024] Quest: Query-Aware Sparsity for Efficient Long-Context LLM Inferenceβ414Jul 10, 2025Updated last year
- An Easy-to-use, Scalable and High-performance Agentic RL Framework based on Ray (PPO & DAPO & REINFORCE++ & VLM & TIS & vLLM & Ray & Asyβ¦β10,167Nov 3, 2026Updated 2 weeks ago
- π₯ A minimal training framework for scaling FLA modelsβ429Apr 22, 2026Updated 6 months ago
- Technical report of Kimina-Prover Preview.β382Jul 10, 2025Updated last year
- slime is an LLM training framework for RL Scaling.β8,842Nov 5, 2026Updated last week
- Efficient Triton Kernels for LLM Trainingβ6,705Updated this week
Are these results useful?