BlinkDL / LinearAttentionArenaLinks
Here we will test various linear attention designs.
☆62Updated last year
Alternatives and similar repositories for LinearAttentionArena
Users that are interested in LinearAttentionArena are comparing it to the libraries listed below
Sorting:
- RWKV-X is a Linear Complexity Hybrid Language Model based on the RWKV architecture, integrating Sparse Attention to improve the model's l…☆47Updated 2 months ago
- Awesome Triton Resources☆34Updated 5 months ago
- ☆49Updated 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
- Xmixers: A collection of SOTA efficient token/channel mixers☆15Updated 3 weeks ago
- Using FlexAttention to compute attention with different masking patterns☆44Updated last year
- Stick-breaking attention☆60Updated 3 months ago
- [ICLR 2025 & COLM 2025] Official PyTorch implementation of the Forgetting Transformer and Adaptive Computation Pruning☆132Updated last week
- ☆56Updated last year
- Code for NeurIPS 2024 Spotlight: "Scaling Laws and Compute-Optimal Training Beyond Fixed Training Durations"☆84Updated 11 months ago
- ☆106Updated last year
- ☆41Updated 5 months ago
- Official code for the paper "Attention as a Hypernetwork"☆42Updated last year
- HGRN2: Gated Linear RNNs with State Expansion☆54Updated last year
- ☆32Updated last year
- Triton implement of bi-directional (non-causal) linear attention☆56Updated 8 months ago
- Fast and memory-efficient exact attention☆70Updated 7 months ago
- Triton Implementation of HyperAttention Algorithm☆48Updated last year
- ☆32Updated last year
- ☆26Updated 2 months ago
- Official Code Repository for the paper "Key-value memory in the brain"☆28Updated 7 months ago
- Linear Attention Sequence Parallelism (LASP)☆86Updated last year
- A repository for research on medium sized language models.☆78Updated last year
- 32 times longer context window than vanilla Transformers and up to 4 times longer than memory efficient Transformers.☆49Updated 2 years ago
- [ICML'24 Oral] The official code of "DiJiang: Efficient Large Language Models through Compact Kernelization", a novel DCT-based linear at…☆102Updated last year
- Explorations into adversarial losses on top of autoregressive loss for language modeling☆38Updated 7 months ago
- ☆89Updated 7 months ago
- GoldFinch and other hybrid transformer components☆45Updated last year
- [NeurIPS 2023 spotlight] Official implementation of HGRN in our NeurIPS 2023 paper - Hierarchically Gated Recurrent Neural Network for Se…☆66Updated last year