.. meta::
    :description lang=en: Large Language Models (LLM) cheat sheet — PyTorch, distributed training, vLLM/SGLang serving, and benchmarking for GPU clusters.
    :keywords: LLM, Large Language Models, PyTorch, vLLM, SGLang, distributed training, model inference, model serving, GPU optimization, CUDA, transformer models, LLM tutorial, LLM cheat sheet

LLM
===

Large Language Models (LLM) training, inference, and optimization. Covers PyTorch
for model development, distributed training across GPUs, vLLM and SGLang for
high-performance LLM inference and serving, and benchmarking tools for measuring
serving performance.

.. toctree::
   :maxdepth: 1

   pytorch
   megatron
   llm-serving
   llm-bench