renll / SeqBoatLinks
[NeurIPS 2023] Sparse Modular Activation for Efficient Sequence Modeling
☆40Updated last year
Alternatives and similar repositories for SeqBoat
Users that are interested in SeqBoat are comparing it to the libraries listed below
Sorting:
- Using FlexAttention to compute attention with different masking patterns☆44Updated 11 months ago
- ☆32Updated last year
- Here we will test various linear attention designs.☆62Updated last year
- ☆49Updated last year
- Sparse Backpropagation for Mixture-of-Expert Training☆30Updated last year
- ☆20Updated last year
- Simple and efficient pytorch-native transformer training and inference (batched)☆78Updated last year
- Efficient PScan implementation in PyTorch☆16Updated last year
- Engineering the state of RNN language models (Mamba, RWKV, etc.)☆32Updated last year
- Official repository of paper "RNNs Are Not Transformers (Yet): The Key Bottleneck on In-context Retrieval"☆27Updated last year
- Official code for the paper "Attention as a Hypernetwork"☆40Updated last year
- ☆26Updated last year
- ☆45Updated last year
- The source code of our work "Prepacking: A Simple Method for Fast Prefilling and Increased Throughput in Large Language Models" [AISTATS …☆61Updated 10 months ago
- ☆56Updated last year
- NAACL '24 (Best Demo Paper RunnerUp) / MlSys @ NeurIPS '23 - RedCoast: A Lightweight Tool to Automate Distributed Training and Inference☆68Updated 8 months ago
- Code for the paper "The Impact of Positional Encoding on Length Generalization in Transformers", NeurIPS 2023☆136Updated last year
- Triton Implementation of HyperAttention Algorithm☆48Updated last year
- Awesome Triton Resources☆33Updated 4 months ago
- ☆81Updated last year
- Implementation of the paper: "Leave No Context Behind: Efficient Infinite Context Transformers with Infini-attention" from Google in pyTO…☆56Updated 2 weeks ago
- Language models scale reliably with over-training and on downstream tasks☆98Updated last year
- ☆19Updated 2 years ago
- Yet another random morning idea to be quickly tried and architecture shared if it works; to allow the transformer to pause for any amount…☆53Updated last year
- ☆51Updated last year
- GoldFinch and other hybrid transformer components☆46Updated last year
- Token Omission Via Attention☆128Updated 10 months ago
- 32 times longer context window than vanilla Transformers and up to 4 times longer than memory efficient Transformers.☆49Updated 2 years ago
- ☆85Updated last year
- Source-to-Source Debuggable Derivatives in Pure Python☆15Updated last year