Deploying Pixtral-12B-Quantised-4-Bit on Serverless GPUs
Deploy serverless GPU applications on your AWS account
Built with developer experience in mind, Tensorkube simplifies the process of deploying serverless GPU apps. In this guide,
we will walk you through the process of deploying Pixtral-12B (4-bit-quantized) on your private cloud.Pixtral-12B is trained to understand both natural images and documents, achieving leading performance on various multimodal benchmarks, surpassing a number of larger models.
Unlike many open-source models, Pixtral is also a cutting-edge text model for its size, and does not compromise on natural language performance to excel in multimodal tasks.
Each tensorkube deployment requires two things - your code and your environment (as a Dockerfile).
While deploying machine learning models, it is beneficial if your model is also a part of your container image. This reduces cold-start times by a significant margin.
To enable this, in addition to a FastAPI app and a dockerfile, we will also write code to download the model and place it in our image file.
We will write a small FastAPI app that loads the model and serves predictions. The FastAPI app will have three endpoints - /readiness, /, and /generate. Remember that the /readiness endpoint is used by Tensorkube to check the health of your deployments.
Pixtral-12B-4Bit is now ready to be deployed on Tensorkube. Navigate to your project root and run the following command:
Copy
Ask AI
tensorkube deploy --gpus 1 --gpu-type a10g
Pixtral-12B-4Bit is now deployed on your AWS account. You can access your app at the URL provided in the output or using the following command:
Copy
Ask AI
tensorkube list deployments
And that’s it! You have successfully deployed Pixtral-12B-4Bit on serverless GPUs using Tensorkube. 🚀To test it out you can run the following command by replacing the URL with the one provided in the output:
Copy
Ask AI
curl -X POST <YOUR_APP_URL_HERE>/generate -H "Content-Type: application/json" -d '{"prompt":"Describe the image.", "images":["https://huggingface.co/datasets/patrickvonplaten/random_img/resolve/main/yosemite.png"]}'
You can also use the readiness endpoint to wake up your nodes in case you are expecting incoming traffic