[GPU] Changed default value for kv cache precision #28502
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
sshlyapn
approved these changes
Jan 20, 2025
vladimir-paramuzov
force-pushed
the
kv_precision
branch
3 times, most recently
from
eb6bc9c to
580f48f
Compare
Signed-off-by: Vladimir Paramuzov <[email protected]>
Signed-off-by: Vladimir Paramuzov <[email protected]>
Signed-off-by: Vladimir Paramuzov <[email protected]>
vladimir-paramuzov
force-pushed
the
kv_precision
branch
from
580f48f to
79d5cb8
Compare
github-merge-queue bot
pushed a commit
that referenced
this pull request
Jan 23, 2025
### Details: - Set default precision of kv cache as fp16 to match inference precision - Update logic which handles multiple apply_user_properties() call for same object to skip everything if config is already finalized. - For platforms with xmx support set `kv_cache_precision` as `inference_precision` to provide correct property query result --------- Signed-off-by: Vladimir Paramuzov <[email protected]>
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Outdated suggestions cannot be applied.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:
kv_cache_precisionasinference_precisionto provide correct property query result