How we fine-tuned FLUX.1-dev for style on the Heroicons library.

How to speed up Whisper transcription with GPU acceleration, smaller models, and parallel processing.

Customize Genmo's open state-of-the-art video generation model Mochi 1 on Modal infrastructure

Which text-to-image model is right for you?

Learn about the cost of Nvidia A100 GPUs and explore top GPU-on-demand platforms for accessing this powerful hardware.

Learn how to select an embedding model for your RAG system

Learn which models to use to segment out objects in images and videos

Learn about the top open-source text-to-video AI models

Learn about the most popular text-to-image diffusion model on the market

Learn how to speed up your model training and inference with Flash Attention

Confused about what each hyperparameter means when you're doing LLM fine-tuning? Our glossary will help.

You want to tailor an LLM to your custom dataset. Should you fine-tune or build a RAG system?

Learn how to create interactive workflows that dynamically adapt to user inputs with Kestra’s open-source orchestration platform and Modal’s serverless infrastructure.

Overview of the top ranking embedding models on the MTEB leaderboard

Learn how to speed up your model training and inference with vLLM or TGI

Learn all about top serverless GPU providers

How do AWS Lambda and Google Cloud Functions compare? This article provides a detailed comparison of these two popular serverless execution environments.

An in-depth look at the differences between Dagster and Airflow for data orchestration

A comprehensive guide to the pricing model for Google Cloud Run functions, including differences between 1st and 2nd gen, CPU and memory allocation, and key pricing metrics. Learn how to optimize your serverless costs.

Explore the relationship between Google Cloud Run and Cloud Run Functions, their key differences, and how to choose the right serverless option for your needs.

Learn about the key differences between RabbitMQ and Apache Kafka, their use cases, and how to choose the right messaging system for your needs.

Learn about gotchas and best practices for serverless inference

A roundup of popular open-source AI agents like OpenHands (formerly OpenDevin), SWE-agent, and Devika.

Serve Meta's foundational Llama 3.1 models via API

Learn how to launch a Jupyter notebook backed by Modal GPUs with this step-by-step guide.

Learn how to run ChatTTS text-to-speech on Modal with this step-by-step guide.

Deploying a Gradio app on Modal

Learn how to run Llama3-405B on Modal with this step-by-step guide.

Learn how to run Ollama on Modal with this step-by-step guide.

Learn how to run XTTS text-to-speech with this step-by-step guide.

Deploying your first Lambda function using AWS SAM

Deep dive on Modal's optimizations for fast, lazy container loading

Learn how to create a serverless solution for uploading JPEG images to Amazon S3 using AWS API Gateway and Lambda with TypeScript

Understand the crucial differences between batch processing and stream processing by example

Estimating VRAM requirements for large language model fine-tuning

Estimating VRAM requirements for large language model inference

Discover the best GPU for your AI workload: Compare A10, A100, and H100 performance, pricing, and use cases to make an informed decision.

Which Stable Diffusion web UI should I use?

Learn the differences between LoRA and QLoRA, two different efficient fine-tuning techniques for large language models.

Explore the top open-source text-to-speech libraries available in 2024, including TortoiseTTS, XTTS, StyleTTS, MeloTTS, OpenVoice v2, and VITS. Learn about their unique features and potential applications.

Optimizations for blazing fast container launches

Learn about the cost of Nvidia H100 GPUs and explore top GPU-on-demand platforms for accessing this powerful hardware.

WhisperX, Deepgram

Axolotl vs. Unsloth vs. Torchtune

Overview of the best open-source llms

A brief explanation of cron jobs, cron syntax, and how to run cron jobs on Modal.