Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

[intel-npu] Adding NPU_DYNAMIC_QUANTIZATION property #28316

Open
wants to merge 2 commits into
base: master
Choose a base branch
from

Conversation

csoka
Copy link
Contributor

@csoka csoka commented Jan 8, 2025

Details:

  • Adding NPU_DYNAMIC_QUANTIZATION public RW boolean property

Tickets:

  • EISW-148716

@csoka csoka requested review from a team as code owners January 8, 2025 12:56
@csoka csoka requested review from akopytko and removed request for a team January 8, 2025 12:56
@github-actions github-actions bot added category: inference OpenVINO Runtime library - Inference category: docs OpenVINO documentation category: CPP API OpenVINO CPP API bindings category: NPU OpenVINO NPU plugin labels Jan 8, 2025
* Set or verify state of dynamic quantization in the NPU compiler
* @ingroup ov_runtime_npu_prop_cpp_api
*/
static constexpr ov::Property<bool> compiler_dynamic_quantization{"NPU_COMPILER_DYNAMIC_QUANTIZATION"};
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

please, add Python API

std::ostringstream dqstr;
dqstr << ov::intel_npu::compiler_dynamic_quantization.name() << KEY_VALUE_SEPARATOR << VALUE_DELIMITER << "\\S+"
<< VALUE_DELIMITER;
logger.warning("COMPILER_DYNAMIC_QUANTIZATION property is not suppored by this compiler version. Removing from "
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

suppored typo

@ZoranZomborat
Copy link
Contributor

@@ -538,6 +538,16 @@ std::string DriverCompilerAdapter::serializeConfig(const Config& config,
content = std::regex_replace(content, std::regex(batchstr.str()), "");
}

// COMPILER_DYNAMIC_QUANTIZATION is not supported in versions < 6.1 - need to remove it
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Version in the comment does not match the implementation

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
category: CPP API OpenVINO CPP API bindings category: docs OpenVINO documentation category: inference OpenVINO Runtime library - Inference category: NPU OpenVINO NPU plugin
Projects
None yet
Development

Successfully merging this pull request may close these issues.

4 participants