updated the assert in BindParams to allow tvm.relax.Constant#17693
Merged
yongwww merged 2 commits intoapache:mainfrom Mar 3, 2025
Merged
updated the assert in BindParams to allow tvm.relax.Constant#17693yongwww merged 2 commits intoapache:mainfrom
yongwww merged 2 commits intoapache:mainfrom
Conversation
ShiboXing
pushed a commit
to ShiboXing/tvm
that referenced
this pull request
Aug 10, 2025
…17693) * updated the assert in BindParams to allow tvm.relax.Constant in the input dictionary * fixed linting
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
2 participants
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
The c++ implementation of BindParams can accept tvm.relax.Constants, however the python interface assert only allows ndarrays. I added tvm.relax.Constant to the assert.
By allowing tvm.relax.Constants as input arguments to BindParams it is possible to avoid duplicating weights if there are several functions in the module that are using the same weight as an input parameter, such as prefill and decode in an LLM.