WIP: Add MultiGPU support #12
Draft
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
YellowRoseCx
changed the title
YellowRoseCx
changed the title
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Outdated suggestions cannot be applied.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.
Goal is to allow multiple GPUs to pool together their VRAM for use during evaluation and quantization. Goal is also to be able to set a maximum amount of memory to use per GPU and have the rest of the data offloaded to CPU RAM.
Motivation: 16gb VRAM GPU runs out of memory evaluating a 30b model on C4-new dataset. It also runs OOM during quantization
I believe a mixture of the current multi-gpu code(for benchmarks) and the CPU offloading scripts will be useful for achieving this