Enable containers on macOS to use the GPU #397
Merged
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
On commit 1329c0a7, llama.cpp's kompute backend acquired the ability to offload Q4_K_M models to a Vulkan-capable GPU. Signed-off-by: Sergio Lopez <[email protected]>
Add a "--gpu" that allows users to request the workload to be offloaded to the GPU. This works natively on macOS using Metal and in containers using Vulkan with llama.cpp's Kompute backend. Signed-off-by: Sergio Lopez <[email protected]>
To be able to properly expose the port outside the container, we need to pass "--host 0.0.0.0" to llama.cpp. Signed-off-by: Sergio Lopez <[email protected]>
|
This one supersedes #235 |
ericcurtin
approved these changes
Oct 31, 2024
rhatdan
reviewed
Oct 31, 2024
| os.getenv("HIP_VISIBLE_DEVICES") or os.getenv("CUDA_VISIBLE_DEVICES")): | ||
| gpu_args = ["-ngl", "99"] | ||
| else: | ||
| print("GPU offload was requested but is not available on this system") |
There was a problem hiding this comment.
Should this be raised as an exception?
There was a problem hiding this comment.
I don't think there's a "right" answer to that question. It's mostly a UX decision. Perhaps it'll be less confusing if we stop the application so the users don't miss the message but, on the other hand, llama.cpp's behavior is to ignore -ngl 99 if there's any kind of problem trying to offload the model to the GPU, so there'll be still plenty of cases in which this may happen.
|
LGTM |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Three changes:
--gpuflag to request the model to be offloaded to the GPU.0.0.0.0so the port can be accessed from outside the container.