piotrpiekos / MoSALinks
User-friendly implementation of the Mixture-of-Sparse-Attention (MoSA). MoSA selects distinct tokens for each head with expert choice routing providing a content-based sparse attention mechanism.
☆25Updated 3 months ago
Alternatives and similar repositories for MoSA
Users that are interested in MoSA are comparing it to the libraries listed below
Sorting:
- HGRN2: Gated Linear RNNs with State Expansion☆55Updated last year
- [NeurIPS 2023 spotlight] Official implementation of HGRN in our NeurIPS 2023 paper - Hierarchically Gated Recurrent Neural Network for Se…☆66Updated last year
- [ICLR 2023] "Sparse MoE as the New Dropout: Scaling Dense and Self-Slimmable Transformers" by Tianlong Chen*, Zhenyu Zhang*, Ajay Jaiswal…☆54Updated 2 years ago
- [ICML 2024] When Linear Attention Meets Autoregressive Decoding: Towards More Effective and Efficient Linearized Large Language Models☆33Updated last year
- A repository for DenseSSMs☆88Updated last year
- Here we will test various linear attention designs.☆62Updated last year
- ☆56Updated last year
- [NAACL 2025] A Closer Look into Mixture-of-Experts in Large Language Models☆54Updated 6 months ago
- Linear Attention Sequence Parallelism (LASP)☆86Updated last year
- ☆85Updated last year
- ☆34Updated 5 months ago
- Using FlexAttention to compute attention with different masking patterns☆44Updated 11 months ago
- Official repository of paper "RNNs Are Not Transformers (Yet): The Key Bottleneck on In-context Retrieval"☆27Updated last year
- DPO, but faster 🚀☆44Updated 8 months ago
- 32 times longer context window than vanilla Transformers and up to 4 times longer than memory efficient Transformers.☆49Updated 2 years ago
- [EMNLP 2022] Official implementation of Transnormer in our EMNLP 2022 paper - The Devil in Linear Transformer☆61Updated 2 years ago
- Code for the paper "Cottention: Linear Transformers With Cosine Attention"☆17Updated 10 months ago
- Code for NeurIPS 2024 Spotlight: "Scaling Laws and Compute-Optimal Training Beyond Fixed Training Durations"☆81Updated 9 months ago
- Implementation of Infini-Transformer in Pytorch☆111Updated 7 months ago
- DeciMamba: Exploring the Length Extrapolation Potential of Mamba (ICLR 2025)☆29Updated 4 months ago
- Stick-breaking attention☆59Updated last month
- ☆33Updated last year
- RWKV-X is a Linear Complexity Hybrid Language Model based on the RWKV architecture, integrating Sparse Attention to improve the model's l…☆46Updated last month
- [ICLR 2025 & COLM 2025] Official PyTorch implementation of the Forgetting Transformer and Adaptive Computation Pruning☆124Updated last week
- MambaFormer in-context learning experiments and implementation for https://arxiv.org/abs/2402.04248☆56Updated last year
- Official implementation of the ICML 2024 paper RoSA (Robust Adaptation)☆42Updated last year
- ☆106Updated last year
- Fast and memory-efficient exact attention☆70Updated 5 months ago
- The official implementation for Gated Attention for Large Language Models: Non-linearity, Sparsity, and Attention-Sink-Free☆46Updated 3 months ago
- Awesome Triton Resources☆33Updated 3 months ago