[CPU] Enable u8 kv cache by default #27454
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
zhangYiIntel
reviewed
Nov 8, 2024
...tel_cpu/tests/functional/custom/subgraph_tests/src/common/concat_transpose_sdp_transpose.cpp
Show resolved
Hide resolved
| @@ -411,6 +412,9 @@ void Config::readProperties(const ov::AnyMap& prop, const ModelType modelType) { | |||
| if (!fcDynamicQuantizationGroupSizeSetExplicitly) { | |||
| fcDynamicQuantizationGroupSize = 0; | |||
| } | |||
| if (!kvCachePrecisionSetExplicitly) { | |||
There was a problem hiding this comment.
why not set kvCachePrecision to u8 here ? To make the kvCachePrecision compatible in ACL platform ? If so, it's better to left a comment here to explain this.
There was a problem hiding this comment.
Setting the kvCachePrecision in constructor should be more clearer and consistent with other properties such as DynamicQuantizationGroup, so my suggestion is to keep them in current style.
luo-cheng2021
force-pushed
the
luocheng/enable_int8_kvcache
branch
2 times, most recently
from
47823da to
16578fe
Compare
3 tasks
alexsu52
pushed a commit
to openvinotoolkit/nncf
that referenced
this pull request
Nov 22, 2024
### Changes explicitly disable kv cache compression to u8, f16 precision is used instead. ### Reason for changes PTWC nightly has a different metrics (ticket 157594). It happens, because since openvinotoolkit/openvino#27454 KV Cache compressed to u8 by default and it affects accuracy of fp32 models (ticket 157571). Propose using kv cache in the f16 in order to handle issues in nncf rather than in ov (there's still an open issue with kv cache compression, and it can be modified in the nearest future) ### Related tickets 157571 157594 ### Tests - [x] openvino-nightly/job/post_training_weight_compression/56  - [x] https://github.com/openvinotoolkit/nncf/actions/runs/11934079602 - [x] job/weekly/job/openvino-nightly/job/test_examples/77
NishantPrabhuFujitsu
pushed a commit
to NishantPrabhuFujitsu/openvino
that referenced
this pull request
Nov 26, 2024
### Details: - *Enable u8 kv cache by default* - *...* ### Tickets: - *[152621](https://jira.devtools.intel.com/browse/CVS-152621)*
github-merge-queue bot
pushed a commit
that referenced
this pull request
Dec 4, 2024
### Details: - *Port for enabling u8 kv cache by default in #27454* ### Tickets: - *[152621](https://jira.devtools.intel.com/browse/CVS-152621)* --------- Co-authored-by: Vladislav Golubev <[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:
Tickets: