A Distributed Attention Towards Linear Scalability for Ultra-Long Context, Heterogeneous Data Training
☆847Jun 12, 2026Updated this week
Alternatives and similar repositories for MagiAttention
Users that are interested in MagiAttention are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- MAGI-1: Autoregressive Video Generation at Scale☆3,706Jun 17, 2025Updated 11 months ago
- Distributed Compiler based on Triton for Parallel Systems☆1,455Apr 22, 2026Updated last month
- A fast communication-overlapping library for tensor/expert parallelism on GPUs.☆1,323Aug 28, 2025Updated 9 months ago
- ☆66Apr 26, 2025Updated last year
- xDiT: A Scalable Inference Engine for Diffusion Transformers (DiTs) with Massive Parallelism☆2,634Jun 8, 2026Updated last week
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- USP: Unified (a.k.a. Hybrid, 2D) Sequence Parallel Attention for Long Context Transformers Model Training and Inference☆672May 21, 2026Updated 3 weeks ago
- Ring attention implementation with flash attention☆1,025Sep 10, 2025Updated 9 months ago
- Quantized Attention on GPU☆44Nov 22, 2024Updated last year
- A unified inference and post-training framework for accelerated video generation.☆3,705Updated this week
- 🐳 Efficient Triton implementations for "Native Sparse Attention: Hardware-Aligned and Natively Trainable Sparse Attention"☆1,006Feb 5, 2026Updated 4 months ago
- Tile primitives for speedy kernels☆3,420May 27, 2026Updated 2 weeks ago
- 🚀 Efficient implementations for emerging model architectures☆5,206Jun 6, 2026Updated last week
- DeeperGEMM: crazy optimized version☆86May 5, 2025Updated last year
- [ICCV 2025] Official repo for "GigaTok: Scaling Visual Tokenizers to 3 Billion Parameters for Autoregressive Image Generation"☆205Jan 7, 2026Updated 5 months ago
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- [ICML2025, NeurIPS2025 Spotlight] Sparse VideoGen 1 & 2: Accelerating Video Diffusion Transformers with Sparse Attention☆681Mar 6, 2026Updated 3 months ago
- ☆52May 19, 2025Updated last year
- DeepGEMM: clean and efficient FP8 GEMM kernels with fine-grained scaling☆25Updated this week
- Helpful tools and examples for working with flex-attention☆1,195May 28, 2026Updated 2 weeks ago
- A library for accelerating Transformer models on NVIDIA GPUs, including using 8-bit and 4-bit floating point (FP8 and FP4) precision on H…☆3,390Updated this week
- VeOmni: Scaling Any Modality Model Training with Model-Centric Distributed Recipe Zoo☆2,013Updated this week
- Accelerate LLM preference tuning via prefix sharing with a single line of code☆53Jul 4, 2025Updated 11 months ago
- ☆121May 19, 2025Updated last year
- [ICML 2025] XAttention: Block Sparse Attention with Antidiagonal Scoring☆281Jul 6, 2025Updated 11 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.
- [ICLR2025, ICML2025, NeurIPS2025 Spotlight] Quantized Attention achieves speedup of 2-5x compared to FlashAttention, without losing end-t…☆3,413Jan 17, 2026Updated 4 months ago
- flex-block-attn: an efficient block sparse attention computation library☆131Dec 26, 2025Updated 5 months ago
- FlashInfer: Kernel Library for LLM Serving☆5,760Jun 8, 2026Updated last week
- [ICML2025] SpargeAttention: A training-free sparse attention that accelerates any model inference.☆1,003Feb 25, 2026Updated 3 months ago
- Dynamic Memory Management for Serving LLMs without PagedAttention☆491Updated this week
- Perplexity GPU Kernels☆586Nov 7, 2025Updated 7 months ago
- ☆37Aug 7, 2025Updated 10 months ago
- ⚡️Write HGEMM from scratch using Tensor Cores with WMMA, MMA and CuTe API, Achieve Peak⚡️ Performance.☆156May 10, 2025Updated last year
- FP16xINT4 LLM inference kernel that can achieve near-ideal ~4x speedups up to medium batchsizes of 16-32 tokens.☆1,086Sep 4, 2024Updated last year
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- ☆267Jul 11, 2024Updated last year
- Muon is Scalable for LLM Training☆1,492Aug 3, 2025Updated 10 months ago
- Domain-specific language designed to streamline the development of high-performance GPU/CPU/Accelerators kernels☆6,489Updated this week
- Flash-Muon: An Efficient Implementation of Muon Optimizer☆251Jun 15, 2025Updated last year
- A sparse attention kernel supporting mix sparse patterns☆520Jan 18, 2026Updated 4 months ago
- VideoSys: An easy and efficient system for video generation☆2,025Aug 27, 2025Updated 9 months ago
- https://wavespeed.ai/ Context parallel attention that accelerates DiT model inference with dynamic caching☆427Jul 5, 2025Updated 11 months ago