AI Agent Skills

A fast, ergonomic and portable tensor library in Nim with a deep learning focus for CPU, GPU and embedded devices via OpenMP, Cuda and OpenCL backends

Run, compile and execute JavaScript for Scientific Computing and Data Visualization TOTALLY TOTALLY TOTALLY in your BROWSER! An open source scientific computing environm…

A GPU accelerated image and video processing framework built on Metal.

BlazingSQL is a lightweight, GPU accelerated, SQL engine for Python. Built on RAPIDS cuDF.

GPU Accelerated t-SNE for CUDA with Python bindings

Cross-Platform, GPU Accelerated Whisper 🏎️

GPU-accelerated data curation for LLM training. Supports text/image/video/audio. Features fuzzy deduplication (16× faster), quality filtering (30+ heuristics), semantic…

Fast GPU OCR server. 270 img/s on FUNSD. TensorRT FP16, PP-OCRv5, HTTP + gRPC.

Multi-cloud orchestration for ML workloads with automatic cost optimization. Use when you need to run training or batch jobs across multiple clouds, leverage spot instan…

⚡ Datoviz: high-performance GPU rendering for scientific data visualization

GPU-accelerated terminal board that puts all your sessions on an infinite canvas

cuCIM - RAPIDS GPU-accelerated image processing library

cuFOLIO is a GPU-accelerated portfolio optimization toolkit for building, backtesting, and scaling modern investment workflows with NVIDIA cuOpt and CUDA-X Data Science.

rapids-singlecell: GPU-accelerated framework for scRNA analysis

Dockerized FastAPI wrapper for Kokoro-82M text-to-speech model w/multiplatform CPU, AMD, NVIDIA GPU PyTorch support, handling, and auto-stitching

Distributed tensors and Machine Learning framework with GPU and MPI acceleration in Python