Enable no-copy API in Model API OVMS Adapter to optimize Embedding endpoint #92
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
This was referenced Oct 29, 2024
dkalinowski
reviewed
Oct 29, 2024
| OVMS_BUFFERTYPE_CPU, | ||
| NOT_USED_NUM)); | ||
| } | ||
| for (const auto& [name, input_tensor] : output) { |
There was a problem hiding this comment.
Suggested change
| for (const auto& [name, input_tensor] : output) { | |
| for (const auto& [name, output_tensor] : output) { |
dkalinowski
reviewed
Oct 29, 2024
| if (std::find(outputsSet.begin(), outputsSet.end(), outputName) == outputsSet.end()) { | ||
| output.emplace(outputName, std::move(makeOvTensor(datatype, shape, dimCount, voutputData, bytesize))); | ||
| } else { | ||
| //output.emplace(outputName, input.at(outputName)); |
There was a problem hiding this comment.
does it mean that we only get selected outputs?
dkalinowski
reviewed
Oct 29, 2024
| @@ -213,6 +324,21 @@ ov::PartialShape OVMSInferenceAdapter::getInputShape(const std::string& inputNam | |||
| } | |||
| return ovShape; | |||
| } | |||
| ov::PartialShape OVMSInferenceAdapter::getOutputShape(const std::string& inputName) const { | |||
There was a problem hiding this comment.
Suggested change
| ov::PartialShape OVMSInferenceAdapter::getOutputShape(const std::string& inputName) const { | |
| ov::PartialShape OVMSInferenceAdapter::getOutputShape(const std::string& outputName) const { |
dkalinowski
reviewed
Oct 29, 2024
| auto it = outShapesMinMaxes.find(inputName); | ||
| if (it == outShapesMinMaxes.end()) { | ||
| LOG(INFO) << "Could not find input:" << inputName; | ||
| throw std::runtime_error(std::string("Adapter could not find input:") + inputName); |
There was a problem hiding this comment.
Suggested change
| throw std::runtime_error(std::string("Adapter could not find input:") + inputName); | |
| throw std::runtime_error(std::string("Adapter could not find output:") + outputName); |
dkalinowski
reviewed
Oct 29, 2024
| @@ -213,6 +324,21 @@ ov::PartialShape OVMSInferenceAdapter::getInputShape(const std::string& inputNam | |||
| } | |||
| return ovShape; | |||
| } | |||
| ov::PartialShape OVMSInferenceAdapter::getOutputShape(const std::string& inputName) const { | |||
| auto it = outShapesMinMaxes.find(inputName); | |||
There was a problem hiding this comment.
Suggested change
| auto it = outShapesMinMaxes.find(inputName); | |
| auto it = outShapesMinMaxes.find(outputName); |
atobiszei
force-pushed
the
atobisze_mp_nocopy
branch
6 times, most recently
from
4de817b to
d493e4e
Compare
atobiszei
force-pushed
the
atobisze_mp_nocopy
branch
from
d493e4e to
f005f1a
Compare
dkalinowski
approved these changes
Nov 4, 2024
| if (std::find(outputsSet.begin(), outputsSet.end(), outputName) == outputsSet.end()) { | ||
| output.emplace(outputName, std::move(makeOvTensor(datatype, shape, dimCount, voutputData, bytesize))); | ||
| } else { | ||
| //output.emplace(outputName, input.at(outputName)); |
There was a problem hiding this comment.
This line should probably be removed
michalkulakowski
approved these changes
Nov 4, 2024
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.
Related changes:
openvinotoolkit/model_server#2763
openvinotoolkit/model_api#212
Ticket: CVS-155477