Merged
Conversation
preetha-intel
force-pushed
the
preetha/device_name_refactor
branch
from
266b797 to
434add6
Compare
|
This PR does not have Device LUID changes. Are they in a separate branch. We need to branch off for UD18 , can we make sure that this PR merges in by today/tomorrow ? |
preetha-intel
force-pushed
the
preetha/device_name_refactor
branch
from
434add6 to
d26fd09
Compare
preetha-intel
requested review from
MayureshV1,
jatinwadhwa921,
saurabhkale17,
sfatimar and
vthaniel
preetha-intel
force-pushed
the
preetha/device_name_refactor
branch
from
2081439 to
cfd6932
Compare
MayureshV1
reviewed
Apr 3, 2025
onnxruntime/core/providers/openvino/openvino_provider_factory.cc
Outdated
Show resolved
Hide resolved
onnxruntime/core/providers/openvino/openvino_provider_factory.cc
Outdated
Show resolved
Hide resolved
preetha-intel
force-pushed
the
preetha/device_name_refactor
branch
from
a456f2d to
2c5a671
Compare
ankitm3k
pushed a commit
that referenced
this pull request
Jul 2, 2025
* Refactor device check logic * Validate the provider options key passed * Add support for mapping LUID to device * Fix lint warnings * generalise LUID for GPU and NPU
This file contains hidden or 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
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
3 participants
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Hi. The PR handles the following JIRA's
https://jira.devtools.intel.com/browse/CVS-165227
https://jira.devtools.intel.com/browse/CVS-164697
https://jira.devtools.intel.com/browse/CVS-165140
These scenarios needs to be validated
For LUID testing,
get the luid of device using python openvino snippet ,
import openvino as ov
core = ov.Core()
luid = core.get_property("GPU.", "DEVICE_LUID")
print luid
This luid can be passed to ovep provider option like ,
ProviderOpitons ov_options;
ov_options[device_type]=AUTO:GPU,CPU;
ov_options[device_luid] = beff000000000000
Checks to be done :
device_type must be set and it should have GPU in it.
For eg :
GPU
AUTO:GPU
AUTO:GPU.0, GPU.1, CPU
device_luid can consist of multiple LUIDs. But they must be comma seperated. Each of the LUID must correspond to a GPU HW. Even if single LUID is incorrect the error must be thrown
Expected output in case of multiple GPU's specified and single LUID is passed is
For device_type=AUTO:GPU.2, GPU.1, GPU.0, CPU and device_luid = beff000000000000 (that corresponds to GPU.1) , then device_type should be
AUTO:GPU.1, CPU