Replace power-of-two batch sizes with max compiled model approach#217
Open
ahsan-ca wants to merge 4 commits intorocm7.2_internal_testingfrom
Open
Replace power-of-two batch sizes with max compiled model approach#217ahsan-ca wants to merge 4 commits intorocm7.2_internal_testingfrom
ahsan-ca wants to merge 4 commits intorocm7.2_internal_testingfrom
Conversation
ebf5a53 to
4a86a96
Compare
4a86a96 to
03c1250
Compare
kahmed10
approved these changes
Feb 20, 2026
1f31434 to
02f8b69
Compare
02f8b69 to
eecc53b
Compare
This file contains hidden or 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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Description
Replace power-of-two batch sizes with max compiled model approach.
ORT_MIGRAPHX_MAX_COMPILED_MODELS=N, such that
max_compiled_models == 1 -> compile the max batch size.
max_compiled_models == 2 -> compile batch size 1 and max batch size.
max_compiled_models >= 3 -> compile batch sizes of 1, some mid values, max.
max_compiled_models == 0 -> set max_compiled_models to 1.
max_compiled_models > max batch size -> set max_compiled_models to max batch size.
This helps to reduce memory usage for higher batch sizes.
Motivation and Context