NX-AI / flashrnnLinks
FlashRNN - Fast RNN Kernels with I/O Awareness
☆91Updated last week
Alternatives and similar repositories for flashrnn
Users that are interested in flashrnn are comparing it to the libraries listed below
Sorting:
- Tiled Flash Linear Attention library for fast and efficient mLSTM Kernels.☆57Updated last month
- Accelerated First Order Parallel Associative Scan☆182Updated 10 months ago
- Work in progress.☆69Updated 2 weeks ago
- The evaluation framework for training-free sparse attention in LLMs☆69Updated last week
- Flash-Muon: An Efficient Implementation of Muon Optimizer☆131Updated last week
- [ICLR 2025] Official PyTorch Implementation of Gated Delta Networks: Improving Mamba2 with Delta Rule☆174Updated 3 months ago
- Official implementation of the paper: "ZClip: Adaptive Spike Mitigation for LLM Pre-Training".☆127Updated 3 weeks ago
- Tree Attention: Topology-aware Decoding for Long-Context Attention on GPU clusters☆126Updated 6 months ago
- Experiment of using Tangent to autodiff triton☆79Updated last year
- Fast and memory-efficient exact attention☆68Updated 3 months ago
- ☆216Updated 2 weeks ago
- Implementation of the proposed Adam-atan2 from Google Deepmind in Pytorch☆108Updated 6 months ago
- Explorations into the recently proposed Taylor Series Linear Attention☆99Updated 10 months ago
- Normalized Transformer (nGPT)☆184Updated 7 months ago
- Here we will test various linear attention designs.☆59Updated last year
- Load compute kernels from the Hub☆191Updated this week
- DPO, but faster 🚀☆43Updated 6 months ago
- JAX bindings for Flash Attention v2☆89Updated 11 months ago
- ☆61Updated 7 months ago
- Pytorch implementation of the PEER block from the paper, Mixture of A Million Experts, by Xu Owen He at Deepmind☆127Updated 10 months ago
- supporting pytorch FSDP for optimizers☆82Updated 6 months ago
- The source code of our work "Prepacking: A Simple Method for Fast Prefilling and Increased Throughput in Large Language Models" [AISTATS …☆59Updated 8 months ago
- ☆36Updated 2 months ago
- A State-Space Model with Rational Transfer Function Representation.☆78Updated last year
- Explorations into the proposal from the paper "Grokfast, Accelerated Grokking by Amplifying Slow Gradients"☆101Updated 6 months ago
- This repository contains the experimental PyTorch native float8 training UX☆224Updated 10 months ago
- RWKV-7: Surpassing GPT☆91Updated 7 months ago
- NanoGPT-speedrunning for the poor T4 enjoyers☆66Updated 2 months ago
- ☆31Updated 7 months ago
- Attempt to make multiple residual streams from Bytedance's Hyper-Connections paper accessible to the public☆85Updated last week