Attention Kernels for Symmetric Power Transformers
☆130Sep 25, 2025Updated 8 months ago
Alternatives and similar repositories for power-attention
Users that are interested in power-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:
- Reference implementation of "Softmax Attention with Constant Cost per Token" (Heinsen, 2024)☆25Jun 6, 2024Updated 2 years ago
- Scalable and Stable Parallelization of Nonlinear RNNS☆31Mar 6, 2026Updated 3 months ago
- sigma-MoE layer☆21Jan 5, 2024Updated 2 years ago
- Transformers components but in Triton☆34May 9, 2025Updated last year
- ☆54May 20, 2024Updated 2 years 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.
- Code for the paper "Function-Space Learning Rates"☆24Jun 3, 2025Updated last year
- ☆35Apr 12, 2024Updated 2 years ago
- Griffin MQA + Hawk Linear RNN Hybrid☆89Apr 13, 2026Updated last month
- ☆61Jul 9, 2024Updated last year
- HGRN2: Gated Linear RNNs with State Expansion☆57Aug 20, 2024Updated last year
- MLX binary vectors and associated algorithms.☆14Mar 13, 2025Updated last year
- ☆19Dec 4, 2025Updated 6 months ago
- POPGym Library in JAX☆14Apr 15, 2024Updated 2 years ago
- 📄Small Batch Size Training for Language Models☆81Mar 18, 2026Updated 2 months ago
- Managed Database hosting by DigitalOcean • AdPostgreSQL, MySQL, MongoDB, Kafka, Valkey, and OpenSearch available. Automatically scale up storage and focus on building your apps.
- Unofficial implementation of paper : Exploring the Space of Key-Value-Query Models with Intention☆12May 24, 2023Updated 3 years ago
- Measuring the Signal to Noise Ratio in Language Model Evaluation☆29Aug 19, 2025Updated 9 months ago
- A bunch of kernels that might make stuff slower 😉☆90Updated this week
- ☆23Oct 22, 2025Updated 7 months ago
- Work in progress.☆80Nov 25, 2025Updated 6 months ago
- Official repository of paper "RNNs Are Not Transformers (Yet): The Key Bottleneck on In-context Retrieval"☆27Apr 17, 2024Updated 2 years ago
- Code for exploring Based models from "Simple linear attention language models balance the recall-throughput tradeoff"☆255Jun 6, 2025Updated last year
- ROSA+: RWKV's ROSA implementation with fallback statistical predictor☆36Oct 13, 2025Updated 7 months ago
- [ICLR'25] "Understanding Bottlenecks of State Space Models through the Lens of Recency and Over-smoothing" by Peihao Wang, Ruisi Cai, Yue…☆18Mar 21, 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.
- JAX Arrays for human consumption☆111Oct 23, 2025Updated 7 months ago
- Language modeling with linear-cost context☆119Sep 25, 2025Updated 8 months ago
- ☆16Sep 22, 2024Updated last year
- ☆125May 28, 2024Updated 2 years ago
- [ICLR 2025 & COLM 2025] Official PyTorch implementation of the Forgetting Transformer and Adaptive Computation Pruning☆150Feb 25, 2026Updated 3 months ago
- ☆85Mar 12, 2026Updated 2 months ago
- ☆33Nov 21, 2025Updated 6 months ago
- NSA Triton Kernels written with GPT5 and Opus 4.1☆70Aug 12, 2025Updated 9 months ago
- [ICML'24 Oral] The official code of "DiJiang: Efficient Large Language Models through Compact Kernelization", a novel DCT-based linear at…☆103Jun 14, 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.
- Pytorch-like dataloaders for JAX.☆103Dec 16, 2025Updated 5 months ago
- seqax = sequence modeling + JAX☆192Jul 23, 2025Updated 10 months ago
- ☆24Sep 25, 2024Updated last year
- Official repository for "BLEUBERI: BLEU is a surprisingly effective reward for instruction following"☆32Jun 5, 2025Updated last year
- ☆18Dec 2, 2024Updated last year
- A fusion of a linear layer and a cross entropy loss, written for pytorch in triton.☆75Aug 2, 2024Updated last year
- Benchmark tests supporting the TiledCUDA library.☆19Nov 19, 2024Updated last year