MoBA: Mixture of Block Attention for Long-Context LLMs
β2,083Apr 3, 2025Updated 11 months ago
Alternatives and similar repositories for MoBA
Users that are interested in MoBA are comparing it to the libraries listed below
Sorting:
- Muon is Scalable for LLM Trainingβ1,446Aug 3, 2025Updated 7 months ago
- π³ Efficient Triton implementations for "Native Sparse Attention: Hardware-Aligned and Natively Trainable Sparse Attention"β977Feb 5, 2026Updated last month
- π Efficient implementations of state-of-the-art linear attention modelsβ4,630Updated this week
- FlashMLA: Efficient Multi-head Latent Attention Kernelsβ12,521Feb 6, 2026Updated last month
- [NeurIPS'24 Spotlight, ICLR'25, ICML'25] To speed up Long-context LLMs' inference, approximate and dynamic sparse calculate the attentionβ¦β1,196Mar 9, 2026Updated last week
- The official repo of MiniMax-Text-01 and MiniMax-VL-01, large-language-model & vision-language-model based on Linear Attentionβ3,362Jul 7, 2025Updated 8 months ago
- A sparse attention kernel supporting mix sparse patternsβ480Jan 18, 2026Updated 2 months ago
- Mooncake is the serving platform for Kimi, a leading LLM service provided by Moonshot AI.β4,921Mar 14, 2026Updated last week
- [ICLR 2025] DuoAttention: Efficient Long-Context LLM Inference with Retrieval and Streaming Headsβ531Feb 10, 2025Updated last year
- FlashInfer: Kernel Library for LLM Servingβ5,145Updated this week
- verl: Volcano Engine Reinforcement Learning for LLMsβ19,919Updated this week
- DeepEP: an efficient expert-parallel communication libraryβ9,053Feb 9, 2026Updated last month
- β810Jun 9, 2025Updated 9 months ago
- Official Repo for Open-Reasoner-Zeroβ2,086Jun 2, 2025Updated 9 months ago
- Kimi-VL: Mixture-of-Experts Vision-Language Model for Multimodal Reasoning, Long-Context Understanding, and Strong Agent Capabilitiesβ1,164Jul 15, 2025Updated 8 months ago
- Distributed Compiler based on Triton for Parallel Systemsβ1,386Mar 11, 2026Updated last week
- [ICML 2024] Quest: Query-Aware Sparsity for Efficient Long-Context LLM Inferenceβ376Jul 10, 2025Updated 8 months ago
- Fast and memory-efficient exact attentionβ22,832Updated this week
- A bidirectional pipeline parallelism algorithm for computation-communication overlap in DeepSeek V3/R1 training.β2,934Jan 14, 2026Updated 2 months ago
- SGLang is a high-performance serving framework for large language models and multimodal models.β24,455Updated this week
- DeepGEMM: clean and efficient FP8 GEMM kernels with fine-grained scalingβ6,268Feb 27, 2026Updated 3 weeks ago
- Production-tested AI infrastructure tools for efficient AGI development and community-driven innovationβ7,972May 15, 2025Updated 10 months ago
- [ICML2025] SpargeAttention: A training-free sparse attention that accelerates any model inference.β961Feb 25, 2026Updated 3 weeks ago
- An Easy-to-use, Scalable and High-performance Agentic RL Framework based on Ray (PPO & DAPO & REINFORCE++ & TIS & vLLM & Ray & Async RL)β9,191Updated this week
- β3,473Mar 7, 2025Updated last year
- A fast communication-overlapping library for tensor/expert parallelism on GPUs.β1,273Aug 28, 2025Updated 6 months ago
- Ongoing research training transformer models at scaleβ15,744Updated this week
- Ring attention implementation with flash attentionβ996Sep 10, 2025Updated 6 months ago
- Helpful tools and examples for working with flex-attentionβ1,157Feb 8, 2026Updated last month
- Expert Parallelism Load Balancerβ1,357Mar 24, 2025Updated 11 months ago
- Domain-specific language designed to streamline the development of high-performance GPU/CPU/Accelerators kernelsβ5,403Updated this week
- Simple RL training for reasoningβ3,841Dec 23, 2025Updated 2 months ago
- Democratizing Reinforcement Learning for LLMsβ5,259Updated this week
- Homepage for ProLong (Princeton long-context language models) and paper "How to Train Long-Context Language Models (Effectively)"β247Sep 12, 2025Updated 6 months ago
- Fully open reproduction of DeepSeek-R1β25,953Nov 24, 2025Updated 3 months ago
- A Distributed Attention Towards Linear Scalability for Ultra-Long Context, Heterogeneous Data Trainingβ676Updated this week
- xDiT: A Scalable Inference Engine for Diffusion Transformers (DiTs) with Massive Parallelismβ2,566Mar 13, 2026Updated last week
- Technical report of Kimina-Prover Preview.β363Jul 10, 2025Updated 8 months ago
- [MLSys'25] QServe: W4A8KV4 Quantization and System Co-design for Efficient LLM Serving; [MLSys'25] LServe: Efficient Long-sequence LLM Seβ¦β818Mar 6, 2025Updated last year