mps-acceleration

Here are 3 public repositories matching this topic...

ejelijah / neural-data-science

A deep learning and neuroscience project for processing fMRI data. Uses Nilearn for functional connectivity mapping and PyTorch for model training, specifically optimized for Apple Silicon (M1/M2/M3) via MPS acceleration. Features automated preprocessing of 48x48 connectivity matrices into 2,304-feature vectors. Built with Python 3.13.

python data-science machine-learning deep-learning neuroscience pytorch neuroimaging nilearn fmri-data-analysis neuro-ai mps-acceleration

Updated Jul 12, 2026
Jupyter Notebook

TJ-Neary / TommyTalker

Star

Privacy-first voice-to-text for macOS. Push-to-talk dictation with app-aware formatting via mlx-whisper on Apple Silicon.

python macos productivity privacy accessibility speech-to-text dictation push-to-talk whisper mlx voice-to-text privacy-first apple-silicon pyqt6 mps-acceleration

Updated Mar 7, 2026
Python

barateza / tq-search

Star

High-performance, fully-batched PyTorch implementation of TurboQuant vector compression optimized for GPU-accelerated similarity search, RAG, and asymmetric retrieval.

pytorch similarity-search vector-quantization rag vector-search mps-acceleration turboquant embeddings-compression asymmetric-scoring

Updated May 23, 2026
Python

Improve this page

Add a description, image, and links to the mps-acceleration topic page so that developers can more easily learn about it.

Curate this topic

Add this topic to your repo

To associate your repository with the mps-acceleration topic, visit your repo's landing page and select "manage topics."

Learn more