maximzubkov / fft-scanLinks
Efficient PScan implementation in PyTorch
☆16Updated last year
Alternatives and similar repositories for fft-scan
Users that are interested in fft-scan are comparing it to the libraries listed below
Sorting:
- Experiments on the impact of depth in transformers and SSMs.☆33Updated 9 months ago
- ☆49Updated last year
- Parallel Associative Scan for Language Models☆18Updated last year
- ☆40Updated 4 months ago
- Triton Implementation of HyperAttention Algorithm☆48Updated last year
- Expanding linear RNN state-transition matrix eigenvalues to include negatives improves state-tracking tasks and language modeling without…☆16Updated 5 months ago
- ☆32Updated last year
- Blog post☆17Updated last year
- ☆56Updated last year
- ☆33Updated last year
- Using FlexAttention to compute attention with different masking patterns☆44Updated 11 months ago
- ☆32Updated 10 months ago
- ☆53Updated last year
- [NeurIPS 2023 spotlight] Official implementation of HGRN in our NeurIPS 2023 paper - Hierarchically Gated Recurrent Neural Network for Se…☆66Updated last year
- ☆11Updated last year
- Reference implementation of "Softmax Attention with Constant Cost per Token" (Heinsen, 2024)☆24Updated last year
- Official repository of paper "RNNs Are Not Transformers (Yet): The Key Bottleneck on In-context Retrieval"☆27Updated last year
- ☆33Updated last year
- ☆37Updated last year
- Xmixers: A collection of SOTA efficient token/channel mixers☆11Updated last month
- Official Code Repository for the paper "Key-value memory in the brain"☆28Updated 6 months ago
- Here we will test various linear attention designs.☆62Updated last year
- Official code for the paper "Attention as a Hypernetwork"☆40Updated last year
- ☆31Updated 9 months ago
- [NeurIPS 2023] Sparse Modular Activation for Efficient Sequence Modeling☆39Updated last year
- ☆56Updated 10 months ago
- Engineering the state of RNN language models (Mamba, RWKV, etc.)☆32Updated last year
- ☆81Updated last year
- ☆44Updated 7 years ago
- Unofficial but Efficient Implementation of "Mamba: Linear-Time Sequence Modeling with Selective State Spaces" in JAX☆86Updated last year