Helpful tools and examples for working with flex-attention
☆1,204Jul 3, 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 PyTorch native platform for training generative AI models☆5,495Updated this week
- 🚀 Efficient implementations for emerging model architectures☆5,279Jun 30, 2026Updated last week
- Tile primitives for speedy kernels☆3,516Jun 15, 2026Updated 3 weeks ago
- Ring attention implementation with flash attention☆1,025Sep 10, 2025Updated 9 months ago
- FlashInfer: Kernel Library for LLM Serving☆5,896Updated this week
- GPU virtual machines on DigitalOcean Gradient AI • AdGet to production fast with high-performance AMD and NVIDIA GPUs you can spin up in seconds. The definition of operational simplicity.
- Efficient Triton Kernels for LLM Training☆6,476Updated this week
- Distributed Compiler based on Triton for Parallel Systems☆1,476Jun 25, 2026Updated 2 weeks ago
- A sparse attention kernel supporting mix sparse patterns☆529Jan 18, 2026Updated 5 months ago
- PyTorch native quantization and sparsity for training and inference☆2,886Updated this week
- 🐳 Efficient Triton implementations for "Native Sparse Attention: Hardware-Aligned and Natively Trainable Sparse Attention"☆1,008Feb 5, 2026Updated 5 months ago
- A Python-embedded DSL that makes it easy to write fast, scalable ML kernels with minimal boilerplate.☆895Updated this week
- A subset of PyTorch's neural network modules, written in Python using OpenAI's Triton.☆606May 13, 2026Updated last month
- Using FlexAttention to compute attention with different masking patterns☆47Sep 22, 2024Updated last year
- A Quirky Assortment of CuTe Kernels☆1,045Updated 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.
- Fast and memory-efficient exact attention☆24,304Jun 29, 2026Updated last 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…☆3,411Updated this week
- A Distributed Attention Towards Linear Scalability for Ultra-Long Context, Heterogeneous Data Training☆865Updated this week
- Applied AI experiments and examples for PyTorch☆322Aug 22, 2025Updated 10 months ago
- Hackable and optimized Transformers building blocks, supporting a composable construction.☆10,513Jun 18, 2026Updated 3 weeks ago
- Minimalistic large language model 3D-parallelism training☆2,737May 26, 2026Updated last month
- USP: Unified (a.k.a. Hybrid, 2D) Sequence Parallel Attention for Long Context Transformers Model Training and Inference☆675May 21, 2026Updated last month
- FlexAttention w/ FlashAttention3 Support☆27Oct 5, 2024Updated last year
- [ICML2025] SpargeAttention: A training-free sparse attention that accelerates any model inference.☆1,008Feb 25, 2026Updated 4 months ago
- End-to-end encrypted email - Proton Mail • AdSpecial offer: 40% Off Yearly / 80% Off First Month. All Proton services are open source and independently audited for security.
- Puzzles for learning Triton☆2,505Apr 1, 2026Updated 3 months ago
- Large Context Attention☆773Oct 13, 2025Updated 8 months ago
- 🔥 A minimal training framework for scaling FLA models☆400Apr 22, 2026Updated 2 months ago
- [ICML 2025] XAttention: Block Sparse Attention with Antidiagonal Scoring☆279Jul 6, 2025Updated last year
- A fast communication-overlapping library for tensor/expert parallelism on GPUs.☆1,332Aug 28, 2025Updated 10 months ago
- Flash-Muon: An Efficient Implementation of Muon Optimizer☆257Jun 15, 2025Updated last year
- Tritonbench is a collection of PyTorch custom operators with example inputs to measure their performance.☆360Updated this week
- [ICLR2025, ICML2025, NeurIPS2025 Spotlight] Quantized Attention achieves speedup of 2-5x compared to FlashAttention, without losing end-t…☆3,449Jan 17, 2026Updated 5 months ago
- Simple and efficient pytorch-native transformer text generation in <1000 LOC of python.☆6,229Aug 22, 2025Updated 10 months ago
- End-to-end encrypted email - Proton Mail • AdSpecial offer: 40% Off Yearly / 80% Off First Month. All Proton services are open source and independently audited for security.
- Mirage Persistent Kernel: Compiling LLMs into a MegaKernel☆2,351Updated this week
- [NeurIPS'24 Spotlight, ICLR'25, ICML'25] To speed up Long-context LLMs' inference, approximate and dynamic sparse calculate the attention…☆1,221Apr 8, 2026Updated 3 months ago
- Domain-specific language designed to streamline the development of high-performance GPU/CPU/Accelerators kernels☆6,592Updated this week
- ☆135May 29, 2025Updated last year
- Triton implementation of FlashAttention2 that adds Custom Masks.☆176Aug 14, 2024Updated last year
- ☆114Mar 12, 2026Updated 3 months ago
- FP16xINT4 LLM inference kernel that can achieve near-ideal ~4x speedups up to medium batchsizes of 16-32 tokens.☆1,102Sep 4, 2024Updated last year