update: Extend datatypes support #482
Open
+18
−0
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
ankitm3k
requested review from
sfatimar,
preetha-intel,
saurabhkale17 and
vthaniel
sfatimar
reviewed
Oct 24, 2024
| @@ -118,6 +118,7 @@ std::vector<SupportedOp> supported_op_mode = { | |||
| {"CumSum", V_2022_1, {"CPU", "GPU"}}, | |||
| {"DepthToSpace", V_2020_4, {"CPU", "GPU"}}, | |||
| {"DequantizeLinear", V_2021_4, {"CPU", "GPU"}}, | |||
| {"DequantizeLinear", V_2024_4, {"CPU", "GPU", "NPU"}}, | |||
There was a problem hiding this comment.
Just add NPU here otherwise it wont support DeQuantizeLinear for 2024_3
There was a problem hiding this comment.
And please merge 2024_5 PR and this one as we do not have support for INT4 in 2024_4
There was a problem hiding this comment.
Just add NPU here otherwise it wont support DeQuantizeLinear for 2024_3
NPU is already added like below -
{"DequantizeLinear", V_2024_4, {"CPU", "GPU", "NPU"}}
Did you mean this instead for support since 2021.4-
{"DequantizeLinear", V_2021_4, {"CPU", "GPU","NPU"}},
ankitm3k
force-pushed
the
ankit/extend_dtype_support
branch
from
c2eca6c
to
945cc2c
Compare
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Outdated suggestions cannot be applied.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.
Description
This PR enables support for INT4 tensors on all the device types in OVEP. This is mandatory to run and support INT4 precision GenAI models