[CPU] [ARM] [INT8] FullyConnected #25171
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
github-actions
bot
added
category: IE Tests
eshoguli
changed the title
eshoguli
force-pushed
the
es/aarch64/int8
branch
from
46e41b5 to
c2d4099
Compare
github-actions
bot
removed
the
category: LP transformations
github-actions
bot
added
category: GPU
eshoguli
changed the title
eshoguli
force-pushed
the
es/aarch64/int8
branch
5 times, most recently
from
b972f54 to
743281f
Compare
eshoguli
force-pushed
the
es/aarch64/int8
branch
5 times, most recently
from
b56d725 to
ea6c2b2
Compare
|
This PR will be closed in a week because of 2 weeks of no activity. |
eshoguli
force-pushed
the
es/aarch64/int8
branch
2 times, most recently
from
af1105f to
0d7c9ec
Compare
github-actions
bot
added
the
category: transformations
Needed changes have been applied. |
alvoron
force-pushed
the
es/aarch64/int8
branch
from
5dc1b5c to
80f626f
Compare
alvoron
force-pushed
the
es/aarch64/int8
branch
from
80f626f to
44e04cf
Compare
| } | ||
|
|
||
| arm_compute::Status ACLLowpFullyConnectedExecutor::validateTensorsInfo(const ACLInfos & aclMemoryInfos) { | ||
| auto &tensor_info = aclMemoryInfos[ACLArgs::ACL_SRC_0]; |
There was a problem hiding this comment.
Just wondering why we are setting dequantization scale on Input port? Logically I would expect it to be applied on dst port
src/plugins/intel_cpu/src/nodes/executors/acl/acl_lowp_fullyconnected.cpp
Outdated
Show resolved
Hide resolved
This reverts commit 9226262.
alvoron
force-pushed
the
es/aarch64/int8
branch
from
af0a528 to
f782508
Compare
dmitry-gorokhov
approved these changes
Dec 18, 2024
| [](const MemoryArgs& memory) -> bool { | ||
| const auto dequantizationScales = getDeQuantizedScales(memory); | ||
| bool isPerChannelQuantization = dequantizationScales.size() > 1; | ||
| // per-channel quantization is not unsupported by ACL |
There was a problem hiding this comment.
minor: "not unsupported"?
11happy
pushed a commit
to 11happy/openvino
that referenced
this pull request
Dec 23, 2024
### Details: - *[ARM] [INT8] FullyConnected* ### Tickets: - *CVS-149494* --------- Co-authored-by: Aleksandr Voron <[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: