glassroom / heinsen_attentionLinks
Reference implementation of "Softmax Attention with Constant Cost per Token" (Heinsen, 2024)
☆24Updated last year
Alternatives and similar repositories for heinsen_attention
Users that are interested in heinsen_attention are comparing it to the libraries listed below
Sorting:
- Official repository of paper "RNNs Are Not Transformers (Yet): The Key Bottleneck on In-context Retrieval"☆27Updated last year
- Here we will test various linear attention designs.☆59Updated last year
- ☆55Updated 11 months ago
- ☆32Updated last year
- ☆23Updated 8 months ago
- ☆32Updated last year
- sigma-MoE layer☆19Updated last year
- ☆48Updated last year
- Official repository for the paper "Approximating Two-Layer Feedforward Networks for Efficient Transformers"☆38Updated 2 weeks ago
- Xmixers: A collection of SOTA efficient token/channel mixers☆11Updated 7 months ago
- HGRN2: Gated Linear RNNs with State Expansion☆55Updated 10 months ago
- ☆20Updated last year
- Blog post☆17Updated last year
- Using FlexAttention to compute attention with different masking patterns☆44Updated 9 months ago
- Official Code Repository for the paper "Key-value memory in the brain"☆26Updated 4 months ago
- 32 times longer context window than vanilla Transformers and up to 4 times longer than memory efficient Transformers.☆48Updated 2 years ago
- ☆15Updated last week
- ☆11Updated last year
- Combining SOAP and MUON☆16Updated 4 months ago
- Triton Implementation of HyperAttention Algorithm☆48Updated last year
- Linear Attention Sequence Parallelism (LASP)☆84Updated last year
- Efficient PScan implementation in PyTorch☆16Updated last year
- [NeurIPS 2023 spotlight] Official implementation of HGRN in our NeurIPS 2023 paper - Hierarchically Gated Recurrent Neural Network for Se…☆65Updated last year
- Triton implement of bi-directional (non-causal) linear attention☆50Updated 4 months ago
- ☆29Updated 2 years ago
- ☆105Updated last year
- [NeurIPS 2023] Sparse Modular Activation for Efficient Sequence Modeling☆37Updated last year
- The implementation for MLSys 2023 paper: "Cuttlefish: Low-rank Model Training without All The Tuning"☆45Updated 2 years ago
- Stick-breaking attention☆57Updated last week
- ☆15Updated last year