Info -> warning: Override performance mode to THROUGHPUT for compilation

[DariaMityagina]

Details:

• Switching performance mode to THROUGHPUT during compilation when PLUGIN batching is applicable is a non-obvious behavior change, we should warn about it.

Tickets:

• ticket-id

AI Assistance:

• AI assistance used: no / yes
• If yes, summarize how AI was used and what human validation was performed (build/tests/manual checks).

[Maxim-Doronin]

What do you think about:

const bool performanceHintSetByUser = properties.find(ov::hint::performance_mode.name()) != properties.end();

auto modifiedConfig = localConfig;

if (!performanceHintSetByUser) {
    _logger.info("Setting performance mode to THROUGHPUT for batched model compilation");
    std::stringstream strStream;
    strStream << ov::hint::PerformanceMode::THROUGHPUT;
    localConfig.update({{ov::hint::performance_mode.name(), strStream.str()}});
    graph = compileWithConfig(std::move(modelToCompile), modifiedConfig);
} else if (localConfig.get<PERFORMANCE_HINT>() == ov::hint::PerformanceMode::LATENCY) {
    _logger.warning("PERFORMANCE_HINT is explicitly set to LATENCY mode, but batch dimension (N) is detected in the model. The NPU Plugin will reshape the model to batch size 1 and process each batch slice separately.");
    _logger.warning("For optimal performance with batched models, THROUGHPUT mode is highly recommended, as LATENCY mode prevents parallel batch processing.");
    _logger.warning("If batch detection appears incorrect, verify that the input and output layouts are configured properly.");
}

[DariaMityagina]

Done, thanks! Good idea!
b1b9bcb

I will run validation with this change.

[DariaMityagina]