initial prototype of dynamic dim selection for models in OnnxRT#231
Draft
TedThemistokleous wants to merge 1 commit intorocm7.2_internal_testingfrom
Draft
initial prototype of dynamic dim selection for models in OnnxRT#231TedThemistokleous wants to merge 1 commit intorocm7.2_internal_testingfrom
TedThemistokleous wants to merge 1 commit intorocm7.2_internal_testingfrom
Conversation
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
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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
Changes to let user select which dimension is dynamic in a model and leverage pad/slice logic so that to MIGraphX the run appears to be static but the specified dimensions are sliced out from the max size of the selected dynamic input
ORT_MIGRAPHX_DYNAMIC_DIMENSIONS_INDEX and ORT_MIGRAPHX_MAX_DYNAMIC_DIM_SIZE are used so that these values specify a non batch dimension and size that we'll also use pad/slice logic for.
Motivation and Context
Helps with customer models that have multiple batch and another dimension that are dynamic, such as sequence length. or other fields. Should allow us to leverage existing logic.