lucidrains / assoc-scanLinks
Associative scan package for DRYing some code between repos
☆17Updated last week
Alternatives and similar repositories for assoc-scan
Users that are interested in assoc-scan are comparing it to the libraries listed below
Sorting:
- Explorations into the recently proposed Taylor Series Linear Attention☆100Updated last year
- Explorations into whether a transformer with RL can direct a genetic algorithm to converge faster☆71Updated 7 months ago
- Implementation of Gradient Agreement Filtering, from Chaubard et al. of Stanford, but for single machine microbatches, in Pytorch☆25Updated 11 months ago
- Implementation and explorations into Blackbox Gradient Sensing (BGS), an evolutionary strategies approach proposed in a Google Deepmind p…☆20Updated 5 months ago
- Exploring an idea where one forgets about efficiency and carries out attention across each edge of the nodes (tokens)☆55Updated 9 months ago
- Implementation of 2-simplicial attention proposed by Clift et al. (2019) and the recent attempt to make practical in Fast and Simplex, Ro…☆46Updated 4 months ago
- Implementation of GateLoop Transformer in Pytorch and Jax☆91Updated last year
- Attempt to make multiple residual streams from Bytedance's Hyper-Connections paper accessible to the public☆139Updated last week
- CUDA implementation of autoregressive linear attention, with all the latest research findings☆46Updated 2 years ago
- Explorations into adversarial losses on top of autoregressive loss for language modeling☆41Updated 3 weeks ago
- Exploration into the proposed "Self Reasoning Tokens" by Felipe Bonetto☆57Updated last year
- The Gaussian Histogram Loss (HL-Gauss) proposed by Imani et al. with a few convenient wrappers for regression, in Pytorch☆71Updated last month
- Implementation of the Kalman Filtering Attention proposed in "Kalman Filtering Attention for User Behavior Modeling in CTR Prediction"☆59Updated 2 years ago
- Implementation of an Attention layer where each head can attend to more than just one token, using coordinate descent to pick topk☆47Updated 2 years ago
- Here we will test various linear attention designs.☆62Updated last year
- Pytorch implementation of a simple way to enable (Stochastic) Frame Averaging for any network☆51Updated last year
- Implementation of the proposed Adam-atan2 from Google Deepmind in Pytorch☆134Updated 3 months ago
- Some personal experiments around routing tokens to different autoregressive attention, akin to mixture-of-experts☆121Updated last year
- Experiment of using Tangent to autodiff triton☆81Updated last year
- Griffin MQA + Hawk Linear RNN Hybrid☆88Updated last year
- Unofficial but Efficient Implementation of "Mamba: Linear-Time Sequence Modeling with Selective State Spaces" in JAX☆92Updated last year
- ☆35Updated last year
- Code for the paper "Function-Space Learning Rates"☆23Updated 7 months ago
- Explorations into the proposal from the paper "Grokfast, Accelerated Grokking by Amplifying Slow Gradients"☆103Updated last year
- research impl of Native Sparse Attention (2502.11089)☆63Updated 10 months ago
- Flash Attention Triton kernel with support for second-order derivatives☆129Updated 3 weeks ago
- ☆34Updated last year
- ☆62Updated last year
- Just some miscellaneous utility functions / decorators / modules related to Pytorch and Accelerate to help speed up implementation of new…☆126Updated last year
- H-Net Dynamic Hierarchical Architecture☆80Updated 4 months ago