A JavaScript version of PyTorch with CUDA acceleration

WebGPU renderer for IFC-Lite

Render-device abstraction, WebGL2/mock backends, buffers, textures, shader modules, materials, render graphs, lighting, shadows, and particle rendering for Aura3D.

CLI tool for creating Modal sandboxes with GitHub repositories

IJavascript is a Javascript kernel for the Jupyter notebook

Linux x64 binaries for Swictation - voice-to-text dictation with GPU acceleration

Node.js / Bun bindings for docling.rs — a Rust port of docling. Convert Markdown, HTML, DOCX, PPTX, XLSX, PDF, images and more into a unified DoclingDocument (Markdown or docling-core JSON).

The best way to integrate TypeGPU into your React app.

Local-first CLI for planning, documentation, and execution workflows with agent assistance.

Sweet Search native binaries for Linux arm64 (glibc) with NVIDIA CUDA backend (candle-cuda + flash-attn) — Jetson Orin, Grace Hopper, and arm64 server GPUs

MCP server for Forge GPU kernel optimization — generate and optimize Triton/CUDA kernels on real H100/A100 GPUs from any AI coding agent

Scrypted OpenVINO Object Detection

CUDA build of docling.rs for Node.js / Bun (Linux x64). Same API as the docling.rs package; binaries are downloaded from the matching GitHub release at install time.

GPU-based force graph layout and rendering

CLI tool for managing vLLM deployments on GPU pods

Runtime GPU texture compression via WebGPU compute shaders, with a WebGL2 fragment-shader fallback. Feed it a PNG/JPG/WebP/AVIF — or an SVG, rasterised on the fly — and get back a GPU-compressed texture (BC7, BC5, ASTC 4x4, BC1, or ETC2) ready for Three.j

[CSS GPU Animation] Marquee Text for vuejs

Jupyterlab extension to detect notebook kernels similarly to how nb_conda_kernel does

提供 koishi skia 服务

MCP server for renting cloud GPUs and running serverless GPU inference from Claude Code or any MCP client — search H100/A100 capacity, deploy vLLM endpoints, and diagnose them.