NX-AI / mlstm_kernelsLinks
Tiled Flash Linear Attention library for fast and efficient mLSTM Kernels.
☆84Updated 2 months ago
Alternatives and similar repositories for mlstm_kernels
Users that are interested in mlstm_kernels are comparing it to the libraries listed below
Sorting:
- FlashRNN - Fast RNN Kernels with I/O Awareness☆174Updated 3 months ago
- DPO, but faster 🚀☆47Updated last year
- Attempt to make multiple residual streams from Bytedance's Hyper-Connections paper accessible to the public☆168Updated 3 weeks ago
- ☆166Updated 3 months ago
- A byte-level decoder architecture that matches the performance of tokenized Transformers.☆67Updated last year
- Implementation of GateLoop Transformer in Pytorch and Jax☆92Updated last year
- Implementation of 2-simplicial attention proposed by Clift et al. (2019) and the recent attempt to make practical in Fast and Simplex, Ro…☆46Updated 5 months ago
- Pytorch implementation of the PEER block from the paper, Mixture of A Million Experts, by Xu Owen He at Deepmind☆135Updated 3 months ago
- RWKV-7: Surpassing GPT☆104Updated last year
- Flash-Muon: An Efficient Implementation of Muon Optimizer☆233Updated 7 months ago
- research impl of Native Sparse Attention (2502.11089)☆63Updated 11 months ago
- ☆67Updated 10 months ago
- Griffin MQA + Hawk Linear RNN Hybrid☆88Updated last year
- Triton Implementation of HyperAttention Algorithm☆48Updated 2 years ago
- https://x.com/BlinkDL_AI/status/1884768989743882276☆28Updated 9 months ago
- Tiny re-implementation of MDM in style of LLaDA and nano-gpt speedrun☆56Updated 10 months ago
- Supporting code for the blog post on modular manifolds.☆115Updated 4 months ago
- Here we will test various linear attention designs.☆62Updated last year
- Collection of autoregressive model implementation☆85Updated 3 weeks ago
- Implementation of the proposed Adam-atan2 from Google Deepmind in Pytorch☆135Updated 3 months ago
- Landing repository for the paper "Softpick: No Attention Sink, No Massive Activations with Rectified Softmax"☆86Updated 4 months ago
- ☆82Updated last year
- Explorations into the proposal from the paper "Grokfast, Accelerated Grokking by Amplifying Slow Gradients"☆103Updated last year
- RWKV is an RNN with transformer-level LLM performance. It can be directly trained like a GPT (parallelizable). So it's combining the best…☆59Updated 10 months ago
- Implementation of a Light Recurrent Unit in Pytorch☆49Updated last year
- Awesome Triton Resources☆39Updated 9 months ago
- PyTorch implementation of models from the Zamba2 series.☆186Updated last year
- ☆70Updated last year
- Normalized Transformer (nGPT)☆198Updated last year
- Explorations into adversarial losses on top of autoregressive loss for language modeling☆41Updated last month