lucidrains / sinkhorn-router-pytorchLinks
Self contained pytorch implementation of a sinkhorn based router, for mixture of experts or otherwise
☆38Updated last year
Alternatives and similar repositories for sinkhorn-router-pytorch
Users that are interested in sinkhorn-router-pytorch are comparing it to the libraries listed below
Sorting:
- Explorations into improving ViTArc with Slot Attention☆43Updated 11 months ago
- Implementation of Infini-Transformer in Pytorch☆113Updated 9 months ago
- Some personal experiments around routing tokens to different autoregressive attention, akin to mixture-of-experts☆122Updated 11 months ago
- Explorations into the recently proposed Taylor Series Linear Attention☆100Updated last year
- Implementation of 2-simplicial attention proposed by Clift et al. (2019) and the recent attempt to make practical in Fast and Simplex, Ro…☆47Updated last month
- Exploration into the proposed "Self Reasoning Tokens" by Felipe Bonetto☆57Updated last year
- Exploration into the Scaling Value Iteration Networks paper, from Schmidhuber's group☆37Updated last year
- Pytorch implementation of the PEER block from the paper, Mixture of A Million Experts, by Xu Owen He at Deepmind☆129Updated last year
- Implementation of GateLoop Transformer in Pytorch and Jax☆90Updated last year
- Implementation of an Attention layer where each head can attend to more than just one token, using coordinate descent to pick topk☆46Updated 2 years ago
- Implementation of the Kalman Filtering Attention proposed in "Kalman Filtering Attention for User Behavior Modeling in CTR Prediction"☆59Updated last year
- Implementation of Agent Attention in Pytorch☆92Updated last year
- The Gaussian Histogram Loss (HL-Gauss) proposed by Imani et al. with a few convenient wrappers for regression, in Pytorch☆66Updated 2 months ago
- [ICLR 2025 & COLM 2025] Official PyTorch implementation of the Forgetting Transformer and Adaptive Computation Pruning☆131Updated 2 weeks ago
- Flash Attention Triton kernel with support for second-order derivatives☆98Updated this week
- Implementation of the proposed Adam-atan2 from Google Deepmind in Pytorch☆125Updated 10 months ago
- Explorations into the proposal from the paper "Grokfast, Accelerated Grokking by Amplifying Slow Gradients"☆102Updated 9 months ago
- Attempt to make multiple residual streams from Bytedance's Hyper-Connections paper accessible to the public☆91Updated 3 months ago
- Implementation of a Light Recurrent Unit in Pytorch☆49Updated last year
- Implementation of a multimodal diffusion transformer in Pytorch☆105Updated last year
- ☆34Updated last year
- Pytorch implementation of a simple way to enable (Stochastic) Frame Averaging for any network☆51Updated last year
- Explorations into whether a transformer with RL can direct a genetic algorithm to converge faster☆71Updated 4 months ago
- ☆58Updated last year
- Exploring an idea where one forgets about efficiency and carries out attention across each edge of the nodes (tokens)☆55Updated 6 months ago
- Just some miscellaneous utility functions / decorators / modules related to Pytorch and Accelerate to help speed up implementation of new…☆123Updated last year
- Implementation of the dynamic chunking mechanism in H-net by Hwang et al. of Carnegie Mellon☆65Updated last month
- Here we will test various linear attention designs.☆61Updated last year
- Why Do We Need Weight Decay in Modern Deep Learning? [NeurIPS 2024]☆67Updated last year
- Official implementation of the paper: "ZClip: Adaptive Spike Mitigation for LLM Pre-Training".☆133Updated last month