Helpful tools and examples for working with flex-attention
☆1,225Aug 17, 2026Updated this week
Alternatives and similar repositories for attention-gym
Users that are interested in attention-gym are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- A Quirky Assortment of CuTe Kernels☆1,116Updated this week
- 🚀 Efficient implementations for emerging model architectures☆5,569Updated this week
- Tile primitives for speedy kernels☆3,631Jul 13, 2026Updated last month
- A PyTorch native platform for training generative AI models☆5,631Updated this week
- A Python-embedded DSL that makes it easy to write fast, scalable ML kernels with minimal boilerplate.☆922Updated this week
- Serverless GPU API endpoints on Runpod - Get Bonus Credits • AdSkip the infrastructure headaches. Auto-scaling, pay-as-you-go, no-ops approach lets you focus on innovating your application.
- A Distributed Attention Towards Linear Scalability for Ultra-Long Context, Heterogeneous Data Training☆914Updated this week
- FlashInfer: Kernel Library for LLM Serving☆6,179Updated this week
- Accelerating MoE with IO and Tile-aware Optimizations☆743Updated this week
- Ring attention implementation with flash attention☆1,045Sep 10, 2025Updated 11 months ago
- Tritonbench is a collection of PyTorch custom operators with example inputs to measure their performance.☆366Updated this week
- Distributed Compiler based on Triton for Parallel Systems☆1,518Updated this week
- PyTorch native quantization for training and inference☆2,947Updated 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…☆3,493Updated this week
- A sparse attention kernel supporting mix sparse patterns☆545Jan 18, 2026Updated 7 months ago
- Managed hosting for WordPress and PHP on Cloudways • AdManaged hosting for WordPress, Magento, Laravel, or PHP apps, on multiple cloud providers. Deploy in minutes on Cloudways by DigitalOcean.
- Efficient Triton Kernels for LLM Training☆6,569Updated this week
- 🐳 Efficient Triton implementations for "Native Sparse Attention: Hardware-Aligned and Natively Trainable Sparse Attention"☆1,018Feb 5, 2026Updated 6 months ago
- Fast and memory-efficient exact attention☆24,727Updated this week
- Mirage Persistent Kernel: Compiling LLMs into a MegaKernel☆2,431Aug 4, 2026Updated last week
- Puzzles for learning Triton☆2,563Apr 1, 2026Updated 4 months ago
- A subset of PyTorch's neural network modules, written in Python using OpenAI's Triton.☆606Updated this week
- [ICML 2025] XAttention: Block Sparse Attention with Antidiagonal Scoring☆281Jul 6, 2025Updated last year
- Hackable and optimized Transformers building blocks, supporting a composable construction.☆10,543Aug 7, 2026Updated last week
- ☆355Updated this week
- Serverless GPU API endpoints on Runpod - Get Bonus Credits • AdSkip the infrastructure headaches. Auto-scaling, pay-as-you-go, no-ops approach lets you focus on innovating your application.
- Applied AI experiments and examples for PyTorch☆323Aug 22, 2025Updated 11 months ago
- Minimalistic large language model 3D-parallelism training☆2,785May 26, 2026Updated 2 months ago
- Domain-specific language designed to streamline the development of high-performance GPU/CPU/Accelerators kernels☆7,232Updated this week
- Kernels, of the mega variety :)☆804May 26, 2026Updated 2 months ago
- ☆138May 29, 2025Updated last year
- [ICML2025] SpargeAttention: A training-free sparse attention that accelerates any model inference.☆1,029Feb 25, 2026Updated 5 months ago
- A fast communication-overlapping library for tensor/expert parallelism on GPUs.☆1,352Aug 28, 2025Updated 11 months ago
- Fast low-bit matmul kernels in Triton☆481Aug 9, 2026Updated last week
- Simple and efficient pytorch-native transformer text generation in <1000 LOC of python.☆6,244Aug 22, 2025Updated 11 months ago
- Proton VPN Special Offer - Get 70% off • AdSpecial partner offer. Trusted by over 100 million users worldwide. Tested, Approved and Recommended by Experts.
- Flash-Muon: An Efficient Implementation of Muon Optimizer☆260Jun 15, 2025Updated last year
- Development repository for the Triton language and compiler☆19,964Updated this week
- USP: Unified (a.k.a. Hybrid, 2D) Sequence Parallel Attention for Long Context Transformers Model Training and Inference☆685May 21, 2026Updated 2 months ago
- [ICLR2025, ICML2025, NeurIPS2025 Spotlight] Quantized Attention achieves speedup of 2-5x compared to FlashAttention, without losing end-t…☆3,648Jan 17, 2026Updated 7 months ago
- Using FlexAttention to compute attention with different masking patterns☆47Sep 22, 2024Updated last year
- Large Context Attention☆774Oct 13, 2025Updated 10 months ago
- CUDA Templates and Python DSLs for High-Performance Linear Algebra☆10,262Updated this week