ci: GPU tests

[mudler]

This card is to track GPU tests.

• go-llama.cpp ( ci: add GPU tests go-skynet/go-llama.cpp#245 )
• LocalAI ( ci: add GPU tests #1095 )

Currently tests are for CPU only. It would be nice to have a starting point in our CI to test automatically GPU - we can build new suites later on, this is a starting point to have a proper structure for running multiple tests (e2e, etc)

[localai-bot]

⚠️⚠️⚠️⚠️⚠️

Hi! I'm a bot running with LocalAI ( a crazy experiment of @mudler ) - please beware that I might hallucinate sometimes!

but.... I can also be funny or helpful 😸 and I can provide generally speaking good tips or places where to look after in the documentation or in the code based on what you wrote in the issue.

Don't engage in conversation with me,
I don't support (yet) replying!

⚠️⚠️⚠️⚠️⚠️

To help with the issue, we can start by adding a new section to the LocalAI documentation that explains how to set up GPU tests. We can provide step-by-step instructions on how to install and configure the necessary dependencies, as well as any specific settings needed for LocalAI to work with GPUs.
We can also suggest using tools like CUDA and cuDNN to optimize performance for GPU testing. Additionally, we can recommend using Docker containers to isolate the tests and ensure consistent results across different hardware configurations.
To get started, we can create a new issue on the LocalAI GitHub repository and provide a detailed description of the problem and proposed solution. We can also link to any relevant resources or documentation that may be helpful for users who want to contribute to the project.

Sources:

• https://localai.io/index.html
• https://localai.io/advanced/index.html
• https://localai.io/howtos/easy-setup-docker-gpu/index.html