Reference implementation of "Self-Attention at Constant Cost per Token via Symmetry-Aware Taylor Approximation" (Heinsen and Kozachkov, 2026)
☆36Feb 21, 2026Updated 5 months ago
Alternatives and similar repositories for sata_attention
Users that are interested in sata_attention are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Implementation of approximate free-energy minimization in PyTorch☆21Oct 16, 2021Updated 4 years ago
- From-scratch PyTorch reproduction of DreamerV4 (Hafner et al., 2025): masked-autoencoder tokenizer, block-causal flow-matching dynamics w…☆37Updated this week
- ☆10May 22, 2023Updated 3 years ago
- Simple and fast parallel scan over sequences of tensors, with any binary associative function you specify, for PyTorch (Franz A. Heinsen,…☆18Apr 15, 2025Updated last year
- A port of the RWKV v7 language model, implemented with the Burn deep learning framework☆14Jun 9, 2025Updated last year
- Managed Database hosting by DigitalOcean • AdPostgreSQL, MySQL, MongoDB, Kafka, Valkey, and OpenSearch available. Automatically scale up storage and focus on building your apps.
- Code for the paper "Cottention: Linear Transformers With Cosine Attention"☆21Nov 15, 2025Updated 9 months ago
- Fun project to run your own LLM chat bot using llama.cpp☆11Jun 9, 2023Updated 3 years ago
- new optimizer☆20Aug 4, 2024Updated 2 years ago
- Julia implementation of flash-attention operation for neural networks.☆11May 31, 2023Updated 3 years ago
- [ICML'26] LEMUR reduces multi-vector retrieval for late interaction models such as ColBERT into regular single-vector retrieval.☆32Jun 21, 2026Updated last month
- This is a comprehensive guide on how you can automate your feature engineering process.☆11Jun 25, 2018Updated 8 years ago
- ☆40Jan 5, 2024Updated 2 years ago
- A novel approach for transformer model introspection that enables saving, compressing, and manipulating internal thought states for advan…☆34Mar 22, 2026Updated 4 months ago
- ☆11Oct 19, 2023Updated 2 years ago
- End-to-end encrypted cloud storage - Proton Drive • AdSpecial offer: 40% Off Yearly / 80% Off First Month. Protect your most important files, photos, and documents from prying eyes.
- Quick ADC☆27May 31, 2019Updated 7 years ago
- Repository for paper Decrypting Cryptic Crosswords☆11Jan 15, 2022Updated 4 years ago
- High performance implementation of the WARP (SIGIR'25) retrieval engine.☆36May 21, 2026Updated 2 months ago
- Powered by ChatterboxTTS | Transformer | Llama | Gradio☆18Sep 7, 2025Updated 11 months ago
- Code for the Avey-B paper (https://arxiv.org/abs/2602.15814)☆32Feb 21, 2026Updated 5 months ago
- ☆14Jul 7, 2024Updated 2 years ago
- ☆10Dec 4, 2023Updated 2 years ago
- High-Performance K-Means Clustering Library☆41Jul 6, 2025Updated last year
- Official Code Repository for the paper "Key-value memory in the brain"☆33Feb 25, 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.
- ☆33Nov 11, 2024Updated last year
- MLX implementation of Hierarchical Reasoning Model (HRM) - Adaptive computation for complex reasoning tasks☆29Aug 27, 2025Updated 11 months ago
- Understand and test language model architectures on synthetic tasks.☆283Mar 22, 2026Updated 4 months ago
- Reimagining Artificial Life for the GPU Era☆28Jul 7, 2026Updated last month