sidijju/NestedTensorsTransformers

Implemented Nested Tensors for Transformers

stars

commits

Python

primary language

Aug 12, 2025

updated

README

Nested Tensors For Transformers

This project sought to conserve memory used in transformer architectures by utilizing PyTorch's beta Nested Tensor feature within the attention mechanisms

Report

Contributors

sidijju

3 commits

Similar repos

GeeeekExplorer/transformers-patch

patches for huggingface transformers to save memory

lamalunderscore/manipulatte

Extensible library for different manipulations of the self-attention mechanism.

extropic-ai/sparse-transformers

Sparse Transformers in JAX

thiomajid/distil_xlstm

Learning Attention Mechanisms through Recurrent Structures

NVIDIA/FasterTransformer

Transformer related optimization, including BERT, GPT

6,446

NVIDIA/TransformerEngine

A library for accelerating Transformer models on NVIDIA GPUs, including using 8-bit and 4-bit…

3,532

CASE-Lab-UMD/LLM-Drop

The official implementation of the paper "Uncovering the Redundancy in Transformers via a Unified…

192

kyegomez/zeta

Build high-performance AI models with modular building blocks

601

Languages

Python

99.7%