⚡️ Lightning AI ORG

Pretrain, finetune ANY AI model of ANY size on 1 or 10,000+ GPUs with zero code changes.

PyTorch Lightning removes repetitive training-loop boilerplate from PyTorch projects so researchers can focus on model design while the framework handles GPUs, checkpoints, and logging.

20+ high-performance LLMs with recipes to pretrain, finetune and deploy at scale.

LitGPT is a Python library with clean, from-scratch implementations of 20+ large language models like Llama 3 and Mistral, covering inference, fine-tuning, and pre-training on any GPU setup.

Implementation of the LLaMA language model based on nanoGPT. Supports flash attention, Int8 and GPTQ 4bit quantization, LoRA and LLaMA-Adapter fine-tuning, pre-training. Apache 2.0-licensed.

A minimal Python framework for building custom AI inference servers with full control over logic, batching, and scaling.

Machine learning metrics for distributed, scalable PyTorch applications.

PyTorch compiler that accelerates training and inference. Get built-in optimizations for performance, memory, parallelism, and easily write your own.

Pytorch Lightning code guideline for conferences

Speed up model training by fixing data loading.

Deep Learning Fundamentals -- Code material and exercises

Collection of Pytorch lightning tutorial form as rich scripts automatically transformed to ipython notebooks.

Lightning Bits: Engineering for Researchers repo

Python pdb for multiple processes

Common Python utilities and GitHub Actions in Lightning Ecosystem

LLM router + minimal agent framework in one. Call any LLM API with OpenAI format. Unified billing, tools, retries, fallback, logging. Build agents and AI apps in pure Python. Full control. Zero magic.

Automate issue discovery for your projects against Lightning nightly and releases.

Save, load, host, and share AI model checkpoints without slowing down training. Host on Lightning AI or your own cloud with enterprise-grade access controls.

A minimal Python logger that tracks everything you try when building AI - metrics, prompts, models, etc, so you can see what changed and why.

Lightning support for Intel Habana accelerators.

No description.

No description.

Multinode templates for Pytorch Lightning

Starter projects for Lightning Studios

Lightweight performance tracker for Python code - zero overhead when disabled.

A framework for few-shot evaluation of autoregressive language models.

Run, manage, and scale AI workloads on any AI infrastructure. Use one system to access & manage all AI compute (Kubernetes, Slurm, 20+ clouds, on-prem).

No description.