DeMoriarty / TorchPQ
Approximate nearest neighbor search with product quantization on GPU in pytorch and cuda
☆221Updated last year
Alternatives and similar repositories for TorchPQ:
Users that are interested in TorchPQ are comparing it to the libraries listed below
- Sinkhorn Transformer - Practical implementation of Sparse Sinkhorn Attention☆260Updated 3 years ago
- Implementation of Linformer for Pytorch☆274Updated last year
- [Prototype] Tools for the concurrent manipulation of variably sized Tensors.☆253Updated 2 years ago
- Official PyTorch Implementation of Long-Short Transformer (NeurIPS 2021).☆225Updated 2 years ago
- Is the attention layer even necessary? (https://arxiv.org/abs/2105.02723)☆484Updated 3 years ago
- Run Effective Large Batch Contrastive Learning Beyond GPU/TPU Memory Constraint☆381Updated last year
- This is a pytorch implementation of k-means clustering algorithm☆302Updated 3 weeks ago
- TF/Keras code for DiffStride, a pooling layer with learnable strides.☆125Updated 3 years ago
- Fully featured implementation of Routing Transformer☆291Updated 3 years ago
- Sequence modeling with Mega.☆295Updated 2 years ago
- Fast Block Sparse Matrices for Pytorch☆546Updated 4 years ago
- An implementation of local windowed attention for language modeling☆429Updated 2 months ago
- ☆376Updated last year
- Implicit MLE: Backpropagating Through Discrete Exponential Family Distributions☆257Updated last year
- Drop-in replacement for any ResNet with a significantly reduced memory footprint and better representation capabilities☆209Updated 11 months ago
- Named tensors with first-class dimensions for PyTorch☆321Updated last year
- Understanding the Difficulty of Training Transformers☆328Updated 2 years ago
- Demystify RAM Usage in Multi-Process Data Loaders☆189Updated last year
- Block-sparse primitives for PyTorch☆154Updated 3 years ago
- The entmax mapping and its loss, a family of sparse softmax alternatives.☆428Updated 9 months ago
- Slicing a PyTorch Tensor Into Parallel Shards☆298Updated 3 years ago
- Differentiable Sorting Networks☆114Updated last year
- Transformer based on a variant of attention that is linear complexity in respect to sequence length☆751Updated 10 months ago
- Library for 8-bit optimizers and quantization routines.☆717Updated 2 years ago
- Implementation of fused cosine similarity attention in the same style as Flash Attention☆212Updated 2 years ago
- Efficient, check-pointed data loading for deep learning with massive data sets.☆205Updated last year
- Accelerate training by storing parameters in one contiguous chunk of memory.☆292Updated 4 years ago
- Differentiable Top-k Classification Learning☆80Updated 2 years ago
- A LARS implementation in PyTorch☆343Updated 5 years ago
- Fast, differentiable sorting and ranking in PyTorch☆799Updated last year