# MAX guides

> MAX developer guides covering deployment, inference, and model development.

Version: Nightly

This file contains links to documentation sections following the llmstxt.org standard.

## Table of Contents

- [Using AI coding assistants](https://docs.modular.com/max/coding-assistants/): Use AI coding assistants such as Cursor, Claude Code, Copilot, and Windsurf with Modular.
- [MAX container](https://docs.modular.com/max/container/): Learn more about the provided Docker container for MAX deployment
- [Benchmark MAX on NVIDIA or AMD GPUs](https://docs.modular.com/max/deploy/benchmark/): Learn how to use our benchmarking script to measure the performance of MAX
- [Deploy MAX on GPU with self-hosted endpoints](https://docs.modular.com/max/deploy/local-to-cloud/): Learn how to deploy MAX pipelines to cloud
- [Basic operations](https://docs.modular.com/max/develop/basic-ops/): Perform tensor operations for arithmetic, shape manipulation, reductions, and random generation
- [Broadcasting](https://docs.modular.com/max/develop/broadcasting/): Learn broadcasting rules, automatic expansion in elementwise ops, and F.broadcast_to for explicit shapes
- [Build custom ops for GPUs](https://docs.modular.com/max/develop/build-custom-ops/): Write custom GPU and CPU operations in Mojo and load them into a MAX graph.
- [Write hardware-agnostic custom ops for PyTorch](https://docs.modular.com/max/develop/custom-kernels-pytorch/): Learn to write custom operators in Mojo for PyTorch
- [Optimize custom ops for GPUs with Mojo](https://docs.modular.com/max/develop/custom-ops-matmul/): Learn to use Mojo's GPU programming abstractions to progressively optimize a matrix multiplication
- [Intro to custom ops](https://docs.modular.com/max/develop/custom-ops/): Extend MAX Graph with custom Mojo kernels for optimized performance
- [Accuracy issues](https://docs.modular.com/max/develop/debugging-accuracy/): Catch NaN and Inf values and uninitialized memory reads in your MAX model with accuracy debugging options.
- [Runtime errors](https://docs.modular.com/max/develop/debugging-errors/): Capture Mojo stack traces and dump compiler IR to investigate unrecoverable failures in your MAX model.
- [GPU errors](https://docs.modular.com/max/develop/debugging-gpu/): Force synchronous GPU execution and enable kernel-level bounds checking to pinpoint the op that caused a failure.
- [Execution tracing](https://docs.modular.com/max/develop/debugging-tracing/): See which operations MAX runs, in what order, and on which device, and map each op back to its Python source.
- [Model debugging overview](https://docs.modular.com/max/develop/debugging/): Review and configure available MAX debugging tools to diagnose issues during model development.
- [Data types (dtype)](https://docs.modular.com/max/develop/dtypes/): Learn how to use dtypes to control tensor precision and interoperability
- [Eager execution](https://docs.modular.com/max/develop/eager-execution/): Use the eager API to create tensors, apply operations, inspect intermediate values, and run a forward pass.
- [Graph overview](https://docs.modular.com/max/develop/graph/): Learn why MAX uses graph compilation and how two programming patterns — explicit graph construction and eager-like execution — both produce graphs.
- [Model development overview](https://docs.modular.com/max/develop/): Learn the process to bring a trained model from Hugging Face to MAX.
- [Indexing and slicing](https://docs.modular.com/max/develop/indexing/): Use slice syntax, F.gather, F.where, and F.scatter to read and write tensor values
- [Layer comparison](https://docs.modular.com/max/develop/layer-comparison/): Localize the first layer where a MAX model diverges from its PyTorch reference by comparing intermediate tensor outputs.
- [Write a custom layer](https://docs.modular.com/max/develop/layers/): Write a custom layer for a model component that max.nn doesn't provide, and connect it to your model.
- [Logit comparison](https://docs.modular.com/max/develop/logit-comparison/): Measure how closely a custom MAX model matches a PyTorch reference using mean absolute error, cosine distance, and KL divergence.
- [Serve a fine-tuned model on a supported architecture](https://docs.modular.com/max/develop/max-pipeline-bring-your-own-model/): Serve a fine-tuned model checkpoint with MAX when the base architecture is already supported, with no architecture code required.
- [Bring up a model with MAX skills](https://docs.modular.com/max/develop/model-bringup-skills/): Learn how to bring up new Hugging Face models in MAX using AI coding agents and MAX skills, including installation, prompting, and verification.
- [Model bring-up workflow](https://docs.modular.com/max/develop/model-bringup-workflow/): Understand MAX's model architecture system and how to implement a custom architecture by mapping config fields, translating weight names, connectin...
- [Build a model graph with Module](https://docs.modular.com/max/develop/modules/): Learn how to compose modules, write custom modules with explicit weights, load checkpoint data, and construct a model graph.
- [Model pipeline](https://docs.modular.com/max/develop/pipelines/): Learn how to integrate your model into a pipeline for serving with MAX.
- [Read a Hugging Face model config](https://docs.modular.com/max/develop/read-model-config/): Translate Hugging Face config.json fields into MAX architecture decisions to identify what to reuse, subclass, or implement.
- [Serve your custom model](https://docs.modular.com/max/develop/serve-custom-model-architectures/): Learn how to serve a model with a custom architecture with max serve and send inference requests to it.
- [Tensor realization](https://docs.modular.com/max/develop/tensor-realization/): Understand how MAX realizes tensors so you can reason about eager performance and write code the graph compiler can optimize.
- [Tensor fundamentals](https://docs.modular.com/max/develop/tensors/): This page provides an overview of tensors, why they matter, and how to create and work with them in MAX.
- [Weight adapters](https://docs.modular.com/max/develop/weight-adapters/): Load a checkpoint into a MAX model by writing a weight adapter that reconciles names, dtypes, and key sets.
- [Environment variables](https://docs.modular.com/max/environment-variables/): Reference for all configurable environment variables in MAX
- [FAQ](https://docs.modular.com/max/faq/): Answers to various questions about the Modular platform.
- [Quickstart](https://docs.modular.com/max/get-started/): A quickstart guide to run a GenAI model locally with Modular.
- [GPU profiling with Nsight Systems](https://docs.modular.com/max/gpu-system-profiling/): How to profile MAX models and endpoints with Nsight Systems.
- [Quantization](https://docs.modular.com/max/graph/quantize/): An introduction to the MAX Graph quantization API
- [Embeddings](https://docs.modular.com/max/inference/embeddings/): Learn how to use the MAX embeddings endpoint to create embeddings for input text
- [Image generation](https://docs.modular.com/max/inference/image-generation/): Generate images from text prompts or transform existing images using the MAX v1/responses endpoint
- [Image and video to text](https://docs.modular.com/max/inference/image-to-text/): Use the MAX chat completions endpoint with image or video input to generate descriptions and answer questions about visual content
- [Text to text](https://docs.modular.com/max/inference/text-to-text/): Generate text using MAX with OpenAI-compatible chat and completion endpoints
- [Video generation](https://docs.modular.com/max/inference/video-generation/): Generate videos from text prompts or animate existing images using the MAX v1/responses endpoint
- [What is Modular](https://docs.modular.com/max/intro/): An overview of the Modular platform, what it does, and how to use it.
- [Supported models](https://docs.modular.com/max/models/): See all the model architectures supported by MAX.
- [Packages](https://docs.modular.com/max/packages/): Learn how to install Modular tools, set up your environment, and choose between nightly and stable versions
- [REST API](https://docs.modular.com/max/rest-api/): The API reference for the MAX inference endpoint.
- [Function calling and tool use](https://docs.modular.com/max/serve/function-calling/): Implement OpenAI-compatible function calling and tool use for agentic GenAI workflows
- [Using LoRA adapters](https://docs.modular.com/max/serve/lora-adapters/): Use LoRA adapters with MAX to serve task-specific, fine-tuned variants of LLMs
- [Prefix caching with PagedAttention](https://docs.modular.com/max/serve/prefix-caching/): Use prefix caching and PagedAttention when serving a model with the MAX CLI
- [Speculative decoding](https://docs.modular.com/max/serve/speculative-decoding/): Use speculative decoding to accelerate LLM inference
- [Structured output](https://docs.modular.com/max/serve/structured-output/): Enable structured output with your GenAI deployments for predictable responses
- [Pixi basics](https://docs.modular.com/pixi/): Pixi is a CLI tool [from Prefix.dev](https://prefix.dev/blog/launching_pixi)