JS runtime lolz

Run the latest LLMs and VLMs across GPU, NPU, and CPU with PC (Python/C++) & mobile (Android & iOS) support, running quickly with OpenAI gpt-oss, Granite4, Qwen3VL, Gemma 3n and more.

Qwen3-VL is the multimodal large language model series developed by Qwen team, Alibaba Cloud.

Instant, controllable, local pre-trained AI models in Rust

A safe Rust FFI binding for the NVIDIA® Tools Extension SDK (NVTX).

Tile primitives for speedy kernels

Minimalist vLLM implementation in Rust

A Pure Rust based LLM (Any LLM based MLLM such as Spark-TTS) Inference Engine, powering by Candle framework.

A high-performance inference engine for AI models

Minimal LLM inference in Rust

Blazingly fast LLM inference.

Democratizing large model inference and training on any device.

Deep learning at the speed of light.

The profiler that gives a unified view of your entire stack - from PyTorch down to GPU

A static site generator for data apps, dashboards, reports, and more. Observable Framework combines JavaScript on the front-end for interactive graphics with any language on the back-end for data a…

An extensible framework for linking databases and interactive views.

Open-source observability for your GenAI or LLM application, based on OpenTelemetry

Safe rust wrapper around CUDA toolkit

Ecosystem of libraries and tools for writing and executing fast GPU code fully in Rust.