emalach / LinearLM
Code for the paper: https://arxiv.org/pdf/2309.06979.pdf
☆19Updated 6 months ago
Alternatives and similar repositories for LinearLM:
Users that are interested in LinearLM are comparing it to the libraries listed below
- Xmixers: A collection of SOTA efficient token/channel mixers☆11Updated 3 months ago
- Awesome Triton Resources☆20Updated 2 months ago
- ☆33Updated last year
- Here we will test various linear attention designs.☆58Updated 9 months ago
- Experiments on the impact of depth in transformers and SSMs.☆22Updated 3 months ago
- ☆11Updated last year
- ☆51Updated 9 months ago
- Code for the note "NF4 Isn't Information Theoretically Optimal (and that's Good)☆18Updated last year
- Official Code Repository for the paper "Key-value memory in the brain"☆22Updated 3 weeks ago
- Stick-breaking attention☆43Updated last month
- ☆47Updated last year
- Blog post☆16Updated last year
- Parallel Associative Scan for Language Models☆18Updated last year
- FlexAttention w/ FlashAttention3 Support☆26Updated 4 months ago
- Implementation of Hyena Hierarchy in JAX☆10Updated last year
- Fast and memory-efficient exact attention☆58Updated this week
- ☆30Updated 11 months ago
- Efficient PScan implementation in PyTorch☆15Updated last year
- ☆49Updated 7 months ago
- Official repository of paper "RNNs Are Not Transformers (Yet): The Key Bottleneck on In-context Retrieval"☆25Updated 10 months ago
- [NeurIPS 2023] Sparse Modular Activation for Efficient Sequence Modeling☆35Updated last year
- Jax implementation of "Griffin: Mixing Gated Linear Recurrences with Local Attention for Efficient Language Models"☆13Updated 9 months ago
- Reference implementation of "Softmax Attention with Constant Cost per Token" (Heinsen, 2024)☆24Updated 8 months ago
- Triton Implementation of HyperAttention Algorithm☆46Updated last year
- Engineering the state of RNN language models (Mamba, RWKV, etc.)☆32Updated 8 months ago
- ☆18Updated 8 months ago
- Using FlexAttention to compute attention with different masking patterns☆40Updated 4 months ago
- Source-to-Source Debuggable Derivatives in Pure Python☆15Updated last year
- ☆22Updated last year