Support forced spreading for multi GPU #4266
Open
+18
−4
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
Our default behavior today is to try to fit into a single GPU if possible. Some users would prefer the old behavior of always spreading across multiple GPUs even if the model can fit into one. This exposes that tunable behavior.
|
This should be good because it's not clear without inferencing a long sequence whether the sequence will fit in memory or not. The model and some default overhead (2k?) might fit but changing the num_ctx parameter to longer may lead to OOM on this single GPU config |
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Outdated suggestions cannot be applied.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.
Our default behavior today is to try to fit into a single GPU if possible. Some users would prefer the old behavior of always spreading across multiple GPUs even if the model can fit into one. This exposes that tunable behavior.
Fixes #4198