facebookresearch / diffqLinks
DiffQ performs differentiable quantization using pseudo quantization noise. It can automatically tune the number of bits used per weight or group of weights, in order to achieve a given trade-off between model size and accuracy.
☆236Updated 2 years ago
Alternatives and similar repositories for diffq
Users that are interested in diffq are comparing it to the libraries listed below
Sorting:
- Memory Efficient Attention (O(sqrt(n)) for Jax and PyTorch☆182Updated 2 years ago
- Implementation of fused cosine similarity attention in the same style as Flash Attention☆217Updated 2 years ago
- Simple and efficient RevNet-Library for PyTorch with XLA and DeepSpeed support and parameter offload☆131Updated 3 years ago
- Make TFRecord Usable Again☆89Updated 2 years ago
- Implementation of a Transformer, but completely in Triton☆276Updated 3 years ago
- graftr: an interactive shell to view and edit PyTorch checkpoints.☆114Updated 5 years ago
- Official code for "Distributed Deep Learning in Open Collaborations" (NeurIPS 2021)☆117Updated 3 years ago
- Online Normalization for Training Neural Networks (Companion Repository)☆86Updated 4 years ago
- Adaptive Gradient Clipping☆149Updated 3 years ago
- Implementation of the specific Transformer architecture from PaLM - Scaling Language Modeling with Pathways - in Jax (Equinox framework)☆188Updated 3 years ago
- A case study of efficient training of large language models using commodity hardware.☆68Updated 3 years ago
- PyTorch implementation of L2L execution algorithm☆108Updated 2 years ago
- Implementation of the Adan (ADAptive Nesterov momentum algorithm) Optimizer in Pytorch☆252Updated 3 years ago
- Implementation of Mega, the Single-head Attention with Multi-headed EMA architecture that currently holds SOTA on Long Range Arena☆206Updated 2 years ago
- Contrastive Language-Audio Pretraining☆88Updated 3 years ago
- TF/Keras code for DiffStride, a pooling layer with learnable strides.☆124Updated 3 years ago
- [Prototype] Tools for the concurrent manipulation of variably sized Tensors.☆251Updated 2 years ago
- Implementation of Fast Transformer in Pytorch☆177Updated 4 years ago
- End-to-end training of sparse deep neural networks with little-to-no performance loss.☆324Updated 2 years ago
- Butterfly matrix multiplication in PyTorch☆174Updated 2 years ago
- ☆66Updated last year
- Named tensors with first-class dimensions for PyTorch☆331Updated 2 years ago
- Implementation of Hourglass Transformer, in Pytorch, from Google and OpenAI☆94Updated 3 years ago
- Continuous Augmented Positional Embeddings (CAPE) implementation for PyTorch☆42Updated 2 years ago
- Accelerate PyTorch models with ONNX Runtime☆365Updated 7 months ago
- Amos optimizer with JEstimator lib.☆82Updated last year
- A small demonstration of using WebDataset with ImageNet and PyTorch Lightning☆75Updated last year
- Approximate nearest neighbor search with product quantization on GPU in pytorch and cuda☆228Updated last year
- Framework for writing deep learning training loops. Lightweight, and retaining full freedom to design as you see fits. It handles checkpo…☆116Updated last year
- ☆164Updated 2 years ago