Revert "[GPU] Fix GPU DynamicQuantize batch consistency (#36078)"#36927
Merged
p-durandin merged 1 commit intoJul 17, 2026
Merged
Conversation
…kit#36078)" This reverts commit 66b9c8e. openvinotoolkit#36078 narrowed the runtime skip of DynamicQuantize in front of FullyConnected. On discrete GPU the FC runs through oneDNN, which then consumes the i8 activation on every token instead of the previous f16 path, causing a decode throughput regression (~+57% 2nd-token latency on Arc A770 for 4-bit LLMs). Integrated GPU was unaffected.
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
4 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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Details
Reverts #36078.
#36078 narrowed the runtime skip of
DynamicQuantizein front ofFullyConnected. On discrete GPU the FC runs through oneDNN, which then consumes the i8 activation on every token instead of the previous f16 path. This caused a decode throughput regression on discrete GPUs (~+57% 2nd-token latency on Arc A770 for 4-bit LLMs, reported on multiple platforms/models). Integrated GPU was unaffected.Reverting to restore the previous behavior while a targeted fix is worked out.