An optimized implementation of the Kimi Linear architecture - a hybrid linear attention mechanism outperforming traditional full attention.
-
Updated
Jun 13, 2026 - Python
GeezerVisonThe World Wide Web, restored to 800 pixels of glory. |
| Home|About|Gaming cabinet|Archives|How it works|Starter sites |
GeezerVison is showing github.com — Build software better, together
#
lang-pythonHere are 302 public repositories matching this topic...Language: All
Filter by language
Sort: Most stars
Sort options
An optimized implementation of the Kimi Linear architecture - a hybrid linear attention mechanism outperforming traditional full attention.
gpu-computing status-active lang-python ai-ml-portfolio status-stable scope-small framework-numpy framework-matplotlib framework-pandas framework-huggingface framework-pytorch gpu-deep-learning gpu-llm
A comprehensive toolkit for developing and benchmarking compression algorithms specifically designed for neural data streams in brain-computer interfaces (BCIs). This project provides efficient, real-time compression solutions that preserve the critical characteristics
gpu-computing status-active lang-python ai-ml-portfolio status-stable scope-medium framework-numpy framework-matplotlib framework-pandas framework-huggingface framework-pytorch framework-scikit-learn framework-cuda ai-ml-portfolio-ml gpu-scientific gpu-deep-learning gdl-bio-neuro
EEG-RAG is a Retrieval-Augmented Generation (RAG) system specifically designed for electroencephalography (EEG) research. It enables researchers, clinicians, and data scientists to ask natural language questions about EEG literature and receive evidence-based answers with proper citations.
gpu-computing lang-python nlp-tools status-experimental ai-ml-portfolio scope-enterprise framework-numpy framework-pandas framework-huggingface framework-pytorch framework-scikit-learn ai-ml-portfolio-rag gpu-deep-learning gpu-rag gpu-nlp gdl-bio-neuro
(NeurIPS 2025), Compact CNNs for EEG decoding: response time prediction and behavioral assessment using competition starter kit infrastructure with custom normalization and training strategies using the Healthy Brain Network (HBN) EEG dataset
gpu-computing status-active lang-python ai-ml-portfolio status-stable scope-enterprise framework-numpy framework-matplotlib framework-pandas framework-plotly framework-pytorch framework-scikit-learn ai-ml-portfolio-ml gpu-deep-learning gdl-bio-neuro
This project demonstrates a comprehensive machine learning pipeline with examples of supervised, unsupervised, and semi-supervised learning approaches. It serves as a template and learning resource for ML practitioners.
gpu-computing status-active lang-python ai-ml-portfolio scope-medium value-educational framework-docker framework-numpy framework-matplotlib framework-pandas framework-plotly framework-pytorch framework-scikit-learn framework-tensorflow ai-ml-portfolio-ml gpu-deep-learning
FastAPI helpers used by the team
This project implements a deep learning pipeline for tumor detection and segmentation in medical images (MRI/CT) using the MONAI framework and PyTorch.
gpu-computing status-active lang-python medical-portfolio scope-medium framework-numpy framework-matplotlib framework-pandas framework-pytorch medical-portfolio-imaging gpu-deep-learning gdl-medical-ai
Detects when a cat walks on your keyboard desktop notification, optional screen lock.
A comprehensive industrial automation platform demonstrating integration between machine vision systems, industrial robots, PLCs, and quality control systems for modern manufacturing applications.
computer-vision status-active lang-python status-stable scope-small framework-docker framework-numpy framework-matplotlib framework-pandas framework-plotly platforms-tools platforms-tools-application platforms-portfolio platforms-portfolio-application gpu-vision
AI-personalized education system with multi-module curriculum spanning OS development, algorithms, DSLs, and mixed reality. ORGAN VI Community project.
education ai curriculum lang-python audience-public kind-tool domain-education organ-vi organvm stage-active family-teaching surface-pages
Professional development environment for PySpark ETL interviews and practice.
hpc status-active lang-python data-analytics-portfolio status-stable scope-large framework-numpy framework-pandas framework-spark data-analytics-processing data-analytics-portfolio-processing
PANhunt searches for credit card numbers (PANs) in directories.
Brain-Forge is an advanced brain-computer interface system that combines cutting-edge neuroimaging technologies to create comprehensive brain scanning, mapping, and simulation capabilities. The platform integrates multi-modal sensor fusion, real-time data processing, and neural simulation to enable unprecedented understanding and modeling of brain
iot gpu-computing status-active lang-python status-finished ai-ml-portfolio scope-medium framework-docker framework-numpy framework-pandas framework-plotly framework-pytorch framework-scikit-learn framework-cuda framework-kubernetes ai-ml-portfolio-ml gpu-scientific gpu-deep-learning gdl-bio-neuro
Source-level patches for AMD ROCm to fix critical memory coherency issues on RDNA1/2 consumer GPUs
gpu-computing status-active lang-python data-analytics-portfolio status-stable scope-enterprise gpu-rocm
QuantumForge is an open-source framework that revolutionizes quantum chemistry calculations by combining the power of GPU acceleration, deep learning, and density functional theory. Built for researchers who demand both accuracy and performance.
gpu-computing lang-python status-experimental ai-ml-portfolio scope-small framework-docker framework-numpy framework-matplotlib framework-pandas framework-plotly framework-pytorch framework-scikit-learn framework-cuda ai-ml-portfolio-ml gpu-scientific gpu-deep-learning gsc-quantum
Architecture governance toolkit — 7-script Python pipeline for risk scoring, drift detection, ownership analysis, and SBOM generation across any codebase
python risk-analysis theory architecture-governance lang-python domain-tooling audience-public kind-tool organ-i organvm stage-active surface-pages
A comprehensive Simultaneous Localization and Mapping (SLAM) implementation in Python with advanced ROS 2 integration, PX4 flight control, and containerized deployment capabilities. This project provides a complete SLAM framework with advanced computer vision techniques and integration capabilities for autonomous navigation applications.
computer-vision robotics devops-infrastructure status-active lang-python devops-portfolio devops-iac status-stable scope-medium devops-portfolio-iac gpu-vision gdl-agentic-ai
The Internet of Space Things (IoST) is a revolutionary platform that brings Internet of Things (IoT) concepts to space exploration, specifically designed to support human spaceflight missions. This project creates an intelligent, interconnected ecosystem of sensors, communication systems, and AI-driven analytics to ensure crew safety,
iot gpu-computing status-active lang-python space-portfolio ai-ml-portfolio status-stable scope-small framework-docker framework-numpy framework-pandas framework-pytorch framework-scikit-learn framework-tensorflow ai-ml-portfolio-ml space-portfolio-orbital gdl-space-ai gpu-deep-learning gds-space-ops
A comprehensive collection of common programming questions, solutions, and best practices covering various topics from coding challenges to security concepts.
computer-vision status-active lang-python status-finished security-portfolio scope-small security-tracking security-tracking-threat security-portfolio-threat gpu-vision
Python project to experiment with bounded spacecraft motion near the binary asteroid system Moshup-Squannit (1999 KW4), inspired by RF3BP pulsating-rotating formulations.
robotics status-active lang-python space-portfolio scope-medium framework-docker framework-numpy framework-matplotlib space-portfolio-simulation gpu-scientific gdl-space-ai gds-simulation
Add this topic to your repoTo associate your repository with the lang-python topic, visit your repo's landing page and select "manage topics." |
| You are visitor 01402520 — GeezerVison does not store the pages you look up. Best viewed with Netscape Navigator 4.7 or Internet Explorer 6 at 800×600. No cookies required. |