mlc-ai ORG

Universal LLM Deployment Engine with ML Compilation

Run AI language models locally on your own laptop, phone, or browser, MLC LLM compiles them to run fast on your specific hardware without sending data to any cloud server.

High-performance In-browser LLM Inference Engine

Runs large language models entirely inside a web browser using the device's graphics card, with no server required, as a drop-in replacement for the OpenAI API.

No description.

No description.

Chat with AI large language models running natively in your browser. Enjoy private, server-free, seamless AI conversations.

Fast, Flexible and Portable Structured Generation

Bringing stable diffusion models to web browsers. Everything runs inside the browser with no server support.

Universal cross-platform tokenizers binding to HF and sentencepiece

No description.

No description.

Compact and Agent-Native MoE Training System

No description.

No description.

AI Assistant running within your browser.

No description.

An interface for AI Agents to interact with various web platforms.

No description.

ML kernels and benchmarking infrastructure written in TIRx

Run LLMs in the Browser with MLC / WebLLM ✨

No description.

The documents for TVM Unity

Relax Training APIs Tutorial and Examples

No description.

A Gradio web UI for Large Language Models. Supports transformers, GPTQ, AWQ, EXL2, llama.cpp (GGUF), Llama models.

No description.

repo for docker related builds

No description.

Evaluate PithTrain, Megatron-LM, TorchTitan on agent-task efficiency.

supporting data for web

modern gpu programming

No description.

No description.

No description.

No description.

Auditing and relabeling cross-distribution Linux wheels.

No description.

Open ABI and FFI for Machine Learning Systems

No description.