Helpful tools and examples for working with flex-attention
☆1,253Sep 26, 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☆1,157Sep 17, 2026Updated last week
- 🚀 Efficient implementations for emerging model architectures☆5,795Updated this week
- Tile primitives for speedy kernels☆3,730Sep 12, 2026Updated 2 weeks ago
- A PyTorch native platform for training generative AI models☆5,771Updated this week
- A Python-embedded DSL that makes it easy to write fast, scalable ML kernels with minimal boilerplate.☆953Updated this 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.
- A Distributed Attention Towards Linear Scalability for Ultra-Long Context, Heterogeneous Data Training☆946Updated this week
- FlashInfer: Kernel Library for LLM Serving☆6,510Updated this week
- Accelerating MoE with IO and Tile-aware Optimizations☆771Aug 29, 2026Updated 3 weeks ago
- Ring attention implementation with flash attention☆1,060Sep 10, 2025Updated last year
- Tritonbench is a collection of PyTorch custom operators with example inputs to measure their performance.☆369Updated this week
- Distributed Compiler and Optimized Parallel Kernels☆1,552Sep 18, 2026Updated last week
- PyTorch native quantization for training and inference☆2,987Updated 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…☆3,555Updated this week
- A sparse attention kernel supporting mix sparse patterns☆557Jan 18, 2026Updated 8 months ago
- 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.
- Efficient Triton Kernels for LLM Training☆6,635Updated this week
- 🐳 Efficient Triton implementations for "Native Sparse Attention: Hardware-Aligned and Natively Trainable Sparse Attention"☆1,023Feb 5, 2026Updated 7 months ago
- Fast and memory-efficient exact attention☆25,022Updated this week
- Mirage Persistent Kernel: Compiling LLMs into a MegaKernel☆2,517Updated this week
- Puzzles for learning Triton☆2,612Apr 1, 2026Updated 5 months ago
- A subset of PyTorch's neural network modules, written in Python using OpenAI's Triton.☆604Aug 14, 2026Updated last month
- [ICML 2025] XAttention: Block Sparse Attention with Antidiagonal Scoring☆282Jul 6, 2025Updated last year
- Hackable and optimized Transformers building blocks, supporting a composable construction.☆10,552Updated this week
- ☆356Updated this week
- 1-Click AI Models by DigitalOcean Gradient • AdDeploy popular AI models on DigitalOcean Gradient GPU virtual machines with just a single click. Zero configuration with optimized deployments.
- Applied AI experiments and examples for PyTorch☆322Aug 22, 2025Updated last year
- Minimalistic large language model 3D-parallelism training☆2,826Updated this week
- Domain-specific language designed to streamline the development of high-performance GPU/CPU/Accelerators kernels☆7,487Updated this week
- Kernels, of the mega variety :)☆835May 26, 2026Updated 4 months ago
- ☆138May 29, 2025Updated last year
- [ICML2025] SpargeAttention: A training-free sparse attention that accelerates any model inference.☆1,252Feb 25, 2026Updated 7 months ago
- A fast communication-overlapping library for tensor/expert parallelism on GPUs.☆1,367Aug 28, 2025Updated last year
- Fast low-bit matmul kernels in Triton☆487Aug 9, 2026Updated last month
- Simple and efficient pytorch-native transformer text generation in <1000 LOC of python.☆6,256Aug 22, 2025Updated last year
- 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.
- Flash-Muon: An Efficient Implementation of Muon Optimizer☆263Jun 15, 2025Updated last year
- Development repository for the Triton language and compiler☆20,247Updated this week
- USP: Unified (a.k.a. Hybrid, 2D) Sequence Parallel Attention for Long Context Transformers Model Training and Inference☆695Sep 16, 2026Updated last week
- [ICLR2025, ICML2025, NeurIPS2025 Spotlight] Quantized Attention achieves speedup of 2-5x compared to FlashAttention, without losing end-t…☆3,950Jan 17, 2026Updated 8 months ago
- Using FlexAttention to compute attention with different masking patterns☆47Sep 22, 2024Updated 2 years ago
- Large Context Attention☆773Oct 13, 2025Updated 11 months ago
- CUDA Templates and Python DSLs for High-Performance Linear Algebra☆10,500Updated this week