FrancescoSaverioZuppichini / Loading-huge-PyTorch-models-with-linear-memory-consumption
Little article showing how to load pytorch's models with linear memory consumption
☆34Updated 2 years ago
Alternatives and similar repositories for Loading-huge-PyTorch-models-with-linear-memory-consumption:
Users that are interested in Loading-huge-PyTorch-models-with-linear-memory-consumption are comparing it to the libraries listed below
- An open source implementation of CLIP.☆32Updated 2 years ago
- Contains my experiments with the `big_vision` repo to train ViTs on ImageNet-1k.☆22Updated 2 years ago
- FID computation in Jax/Flax.☆27Updated 8 months ago
- Another attempt at a long-context / efficient transformer by me☆37Updated 2 years ago
- Memory-Efficient CUDA kernels for training ConvNets with PyTorch.☆38Updated 3 weeks ago
- ☆73Updated 2 years ago
- PyTorch interface for TrueGrad Optimizers☆42Updated last year
- ☆29Updated 2 years ago
- Utilities for PyTorch distributed☆23Updated 2 weeks ago
- Implementation of some personal helper functions for Einops, my most favorite tensor manipulation library ❤️☆54Updated 2 years ago
- A GPT, made only of MLPs, in Jax☆57Updated 3 years ago
- Exploring an idea where one forgets about efficiency and carries out attention across each edge of the nodes (tokens)☆45Updated last month
- Implementation of the Kalman Filtering Attention proposed in "Kalman Filtering Attention for User Behavior Modeling in CTR Prediction"☆57Updated last year
- Implementation of a Transformer using ReLA (Rectified Linear Attention) from https://arxiv.org/abs/2104.07012☆49Updated 2 years ago
- Implementation of LogAvgExp for Pytorch☆34Updated 2 years ago
- Implementation of "compositional attention" from MILA, a multi-head attention variant that is reframed as a two-step attention process wi…☆50Updated 2 years ago
- Automatically take good care of your preemptible TPUs☆36Updated last year
- HomebrewNLP in JAX flavour for maintable TPU-Training☆48Updated last year
- A simple Transformer where the softmax has been replaced with normalization☆19Updated 4 years ago
- ☆28Updated 3 years ago
- Pixel Parsing. A reproduction of OCR-free end-to-end document understanding models with open data☆21Updated 7 months ago
- A dashboard for exploring timm learning rate schedulers☆19Updated 3 months ago
- Implementation of Token Shift GPT - An autoregressive model that solely relies on shifting the sequence space for mixing☆48Updated 3 years ago
- Just some miscellaneous utility functions / decorators / modules related to Pytorch and Accelerate to help speed up implementation of new…☆120Updated 7 months ago
- Simple python template☆40Updated 10 months ago
- Implementation of Kronecker Attention in Pytorch☆18Updated 4 years ago
- Re-implementation of 'Grokking: Generalization beyond overfitting on small algorithmic datasets'☆38Updated 3 years ago
- Hacks for PyTorch☆18Updated last year
- ☆24Updated 2 years ago
- CLOOB training (JAX) and inference (JAX and PyTorch)☆70Updated 2 years ago