fix(intel): Set GPU vendor on Intel images and cleanup #5945
Conversation
✅ Deploy Preview for localai ready!
To edit notification comments on pull requests, go to your Netlify project configuration. |
github-actions
bot
added
kind/documentation
| @@ -109,24 +109,15 @@ jobs: | |||
| skip-drivers: 'false' | |||
| makeflags: "--jobs=4 --output-sync=target" | |||
| aio: "-aio-gpu-vulkan" | |||
| - build-type: 'sycl_f16' | |||
| - build-type: 'sycl' | |||
There was a problem hiding this comment.
shall we simply put intel here? this is not used anywhere else now, backends have their own build_type
There was a problem hiding this comment.
I dunno, Intel seem to have multiple options and I'm not sure if oneapi would cover all of them.
There was a problem hiding this comment.
but it's what Intel suggest and are the basic dependency to get going with an intel GPU (common enough for all the other backends). I'd really go simple here and name it intel. Users don't have to learn internals until they want to.
| @@ -166,7 +162,7 @@ docker run -ti --name local-ai -p 8080:8080 --gpus all localai/localai:latest-ai | |||
| docker run -ti --name local-ai -p 8080:8080 --gpus all localai/localai:latest-aio-gpu-nvidia-cuda-11 | |||
|
|
|||
| # Intel GPU version | |||
| docker run -ti --name local-ai -p 8080:8080 localai/localai:latest-aio-gpu-intel-f16 | |||
There was a problem hiding this comment.
I think we need to update also the https://github.com/mudler/LocalAI/blob/master/docs/static/install.sh script, and I guess documentation too. Maybe better to grep the codebase
There was a problem hiding this comment.
I did, but not for the right thing I think.
I'm a bit confused about the AIO image and how this works now. Does it include the backends or are these downloaded? I can't see how that would happen. If they are included then it would make sense to keep the f16 and f32 versions perhaps, but presently I have removed them.
There was a problem hiding this comment.
all downloaded during start, there aren't anymore backends in any image 👍
Signed-off-by: Richard Palethorpe <[email protected]>
mudler
added
breaking-change
bug
Description
Set /var/localai/capability so that the SYCL backends are downloaded. Also remove the f16 and f32 builds for the core image because they are now identical, only the GGML based backends have this distinction.
Also some other bits have been removed and cleaned up.
Notes for Reviewers
Signed commits