Modified qwen_2.5 modelling file to allow replicate_kv_script to work for custom num_kv_heads.#595
Closed
quic-dhirajku wants to merge 1 commit into
Closed
Conversation
… for custom num_kv_heads. Edited the replicate_kv_heads script to allow loading the VLM and export properly after KV_heads update. Signed-off-by: quic-dhirajku <quic_dhirajku@quicinc.com> ## Export goes through successfuly, need to export full model for it to work due to TF version issues.
quic-dhirajku
requested review from
ochougul,
quic-amitraj,
quic-hemagnih and
quic-rishinr
as code owners
Contributor
|
Hi @quic-dhirajku as discussed please raise a ticket for SIT to verify the Perf hit. In case if we are good from perf side and CI then lets go ahead and merge it. In parallel we can work on below PR |
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Edited the replicate_kv_heads script to allow loading the VLM and export properly after KV_heads update.
Export goes through successfuly, need to export full model for it to work due to TF version issues.