# How to Use Model Weights Stored in Tigris with SkyPilot The most common way to deploy AI models in production is by using “serverless” inference. This means that every time you get a request, you don’t know what state the underlying hardware is in. You don’t know if you have your models cached, and in the worst case you need to do a cold start and download your model weights from scratch. A couple fixable problems arise when running your models on serverless or any frequently changing infrastructure: * Model distribution that's not optimized for latency causes needless GPU idle time as the model weights are downloaded to the machine on cold start. Tigris behaves like a content delivery network by default and is designed for low latency, saving idle time on cold start. * Compliance restrictions like data sovereignty and GDPR increase complexity quickly. Tigris makes regional restrictions a one-line configuration, guide [here](/docs/buckets/locations/.md). * Reliance on third party caches for distributing models creates an upstream dependency and leaves your system vulnerable to downtime. Tigris guarantees 99.99% availability with [public availability data](https://www.tigrisdata.com/blog/availability-metrics-public/). ## SkyPilot[​](#skypilot "Direct link to SkyPilot") [SkyPilot](https://skypilot.readthedocs.io/en/latest/docs/index.html) is a tool that lets you route GPU compute to the cheapest possible locale based on your requirements. The same configuration lets you control AWS, Azure, Google Cloud, Oracle Cloud, Kubernetes, Runpod, Fluidstack, or more. For more information about Skypilot, check out [their documentation](https://skypilot.readthedocs.io/en/latest/docs/index.html). To get started, you'll need to install SkyPilot [following their directions](https://skypilot.readthedocs.io/en/latest/getting-started/installation.html). Be sure to have [Conda](https://anaconda.org/anaconda/conda) installed. You will need to configure your cloud of choice for this example. See [SkyPilot's documentation](https://skypilot.readthedocs.io/en/latest/getting-started/installation.html#cloud-account-setup) on how to do this. We have tested this against a few clouds: * [AWS](https://aws.amazon.com/) * [Lambda](https://lambdalabs.com/) * [Runpod](https://www.runpod.io/) However the other providers should work fine. ## Usecase[​](#usecase "Direct link to Usecase") You can put AI model weights into Tigris so that they are cached and fast no matter where you’re inferencing from. This allows you to have cold starts be faster and you can take advantage of Tigris' [globally distributed architecture](/docs/overview/.md), enabling your workloads to start quickly no matter where they are in the world. For this example, we’ll set up [SDXL Lightning](https://huggingface.co/ByteDance/SDXL-Lightning) by ByteDance for inference with the weights stored in Tigris. ## Getting Started[​](#getting-started "Direct link to Getting Started") Download the `sdxl-in-tigris` template from GitHub: ``` git clone https://github.com/tigrisdata-community/sdxl-in-tigris ``` Prerequisite tools In order to run this example locally, you need these tools installed: * Python 3.11 * pipenv * The AWS CLI Also be sure to configure the AWS CLI for use with Tigris: [Configuring the AWS CLI](/docs/sdks/s3/aws-cli/.md). To build a custom variant of the image, you need these tools installed: * Mac/Windows: [Docker Desktop app](https://www.docker.com/products/docker-desktop/), alternatives such as Podman Desktop will not work. * Linux: Docker daemon, alternatives such as Podman will not work. * [Replicate's cog tool](https://github.com/replicate/cog) * [jq](https://jqlang.github.io/jq/) To install all of the tool depedencies at once, clone the template repo and run `brew bundle`. Create a new bucket for generated images, it’ll be called `generated-images` in this article. ``` aws s3 create-bucket --acl private generated-images ``` Optional: upload your own model If you want to upload your own models, create a bucket for this. It'll be referred to as `model-storage-demo` in this tutorial. Both of these buckets should be private. Then activate the virtual environment with `pipenv shell` and install the dependencies for uploading a model: ``` pipenv shell --python 3.11 pip install -r requirements.txt ``` Run the `prepare_model` script to massage and upload a Stable Diffusion XL model or finetune to Tigris: ``` python scripts/prepare_model.py ByteDance/SDXL-Lightning model-storage ``` info Want differently styled images? Try finetunes like [Kohaku XL](https://huggingface.co/KBlueLeaf/Kohaku-XL-Zeta)! Pass the Hugging Face repo name to the `prepare_model` script like this: ``` python scripts/prepare_model.py KBlueLeaf/Kohaku-XL-Zeta model-storage ``` ## Access keys[​](#access-keys "Direct link to Access keys") Create a new access key in the [Tigris Dashboard](https://console.storage.dev) and grant it access to the required buckets (e.g., `model-storage-demo` and `generated-images`). Copy the access key ID and secret access keys into either your notes or a password manager, you will not be able to see them again. These credentials will be used later to deploy your app in the cloud. This keypair will be referred to as the `workload-keypair` in this tutorial. ## Customizing the `skypilot.yaml` file[​](#customizing-the-skypilotyaml-file "Direct link to customizing-the-skypilotyaml-file") Open `skypilot.yaml` in your favorite text editor. Customize the environment variables in the `envs:` key: ``` envs: # Tigris config AWS_ACCESS_KEY_ID: tid_AzureDiamond # workload access key ID AWS_SECRET_ACCESS_KEY: tsec_hunter2 # workload secret access key AWS_ENDPOINT_URL_S3: https://t3.storage.dev AWS_REGION: auto # Bucket names MODEL_BUCKET_NAME: model-storage-demo PUBLIC_BUCKET_NAME: generated-images # Model to load MODEL_PATH: ByteDance/SDXL-Lightning ``` | Envvar name | Value | | ----------------------- | ------------------------------------------------------------------ | | `AWS_ACCESS_KEY_ID` | The access key ID from the workload keypair | | `AWS_SECRET_ACCESS_KEY` | The secret access key from the workload keypair | | `AWS_ENDPOINT_URL_S3` | `https://t3.storage.dev` | | `AWS_REGION` | `auto` | | `MODEL_PATH` | `ByteDance/SDXL-Lightning` | | `MODEL_BUCKET_NAME` | `model-storage-demo` (Optional: replace with your own bucket name) | | `PUBLIC_BUCKET_NAME` | `generated-images` (replace with your own bucket name) | ## Launching it in a cloud[​](#launching-it-in-a-cloud "Direct link to Launching it in a cloud") Run `sky serve up` to start the image in a cloud: ``` sky serve up skypilot.yaml -n sdxl ``` Wait a few minutes for everything to converge, and then you can use the endpoint URL to poke it: ``` ⚙︎ Service registered. Service name: sdxl Endpoint URL: 3.84.60.169:30001 ``` note You can run `sky serve status` to find out if your endpoint is ready: ``` $ sky serve status <...> Service Replicas SERVICE_NAME ID VERSION ENDPOINT LAUNCHED RESOURCES STATUS REGION sdxl 1 1 http://69.30.85.69:22112 47 secs ago 1x RunPod({'RTXA4000': 1}) READY CA ``` Finally, run a test generation with this curl command: ``` curl "http://ip:port/predictions/$(uuidgen)" \ -X PUT \ -H "Content-Type: application/json" \ --data-binary '{ "input": { "prompt": "The space needle in Seattle, best quality, masterpiece", "aspect_ratio": "1:1", "guidance_scale": 3.5, "num_inference_steps": 4, "max_sequence_length": 512, "output_format": "png", "num_outputs": 1 } }' ``` If all goes well, you should get an image like this: ![The word \'success\' in front of the Space Needle](/docs/assets/images/success-0dbeb88b06e1f75e204b2f30396ab7f4.webp) You can destroy the machine with this command: ``` sky serve down sdxl ```