Fix (GPFQ): use max/mean to avoid running out of memory #890
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
fabianandresgrob
force-pushed
the
fix/gpfq_memory_error
branch
from
8853566
to
59f8ea4
Compare
fabianandresgrob
force-pushed
the
fix/gpfq_memory_error
branch
from
59f8ea4
to
25e8735
Compare
|
Closing this since it seems to provide poorer performances compared to standard implementation |
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Outdated suggestions cannot be applied.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.
For the GPFQ algorithm, larger models lead to an OutOfMemory error. This is because the GPFQ algorithm uses all calibration data provided. Instead of iteratively concatenating the new input to all previous ones, we could use a running average, or always select the max of the new input and the previous ones.