[GPU] Integrate dynamic quantization for onednn #26940
Merged
Conversation
This file contains 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
isanghao
force-pushed
the
dyn_quan_gs
branch
from
4b87ec6 to
ee3b6e8
Compare
It works with group_size, but only for dyn_quan_ref workaround for onednn accuracy issue dyn_quan_opt is implemented bug fix test fix do not use dyn_quan for u8 wei and wzp fix after rebase dyn_quan group size test
TODO: * Check sym e2e accuracy * check asym e2e accuracy * test case for dyn_quan_opt for asym
|
This PR will be closed in a week because of 2 weeks of no activity. |
isanghao
changed the title
byungilm
approved these changes
Dec 4, 2024
github-merge-queue
bot
removed this pull request from the merge queue due to failed status checks
github-merge-queue bot
pushed a commit
that referenced
this pull request
Dec 9, 2024
### Details: - Integrated grouped dynamic quantization from onednn - Integrated asymmetric per-token dynamic quantization from onednn - Those are not enabled by default, yet ### Tickets: - 148732, 157869, 157589
github-merge-queue
bot
removed this pull request from the merge queue due to failed status checks
11happy
pushed a commit
to 11happy/openvino
that referenced
this pull request
Dec 23, 2024
### Details: - Integrated grouped dynamic quantization from onednn - Integrated asymmetric per-token dynamic quantization from onednn - Those are not enabled by default, yet ### Tickets: - 148732, 157869, 157589
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Outdated suggestions cannot be applied.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.
Details:
Tickets: