You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
[GPU] Dynamic element type instead of undefined. Earlier config finalize call (#29127)
### Details:
- Call config.finalize() in program's c-tor earlier to ensure that
options are actually applied in unit tests.
- Replaced deprecated `undefined` element type with `dynamic`
Signed-off-by: Vladimir Paramuzov <vladimir.paramuzov@intel.com>
Copy file name to clipboardexpand all lines: src/plugins/intel_gpu/include/intel_gpu/runtime/options.inl
+2-2
Original file line number
Diff line number
Diff line change
@@ -8,7 +8,7 @@ OV_CONFIG_RELEASE_OPTION(ov::device, id, "0", "ID of the current device")
8
8
OV_CONFIG_RELEASE_OPTION(ov, cache_dir, "", "Directory where model cache can be stored. Caching is disabled if empty")
9
9
OV_CONFIG_RELEASE_OPTION(ov, num_streams, 1, "Number of streams to be used for inference")
10
10
OV_CONFIG_RELEASE_OPTION(ov, compilation_num_threads, std::max(1, static_cast<int>(std::thread::hardware_concurrency())), "Max number of CPU threads used for model compilation for the stages that supports parallelism")
11
-
OV_CONFIG_RELEASE_OPTION(ov::hint, inference_precision, ov::element::f16, "Model floating-point inference precision. Supported values: { f16, f32, undefined }", [](ov::element::Type t) { return t == ov::element::f16 || t == ov::element::f32 || t == ov::element::undefined; })
11
+
OV_CONFIG_RELEASE_OPTION(ov::hint, inference_precision, ov::element::f16, "Model floating-point inference precision. Supported values: { f16, f32, dynamic }", [](ov::element::Type t) { return t == ov::element::f16 || t == ov::element::f32 || t == ov::element::dynamic; })
12
12
OV_CONFIG_RELEASE_OPTION(ov::hint, model_priority, ov::hint::Priority::MEDIUM, "High-level hint that defines the priority of the model. It may impact number of threads used for model compilton and inference as well as device queue settings")
13
13
OV_CONFIG_RELEASE_OPTION(ov::hint, performance_mode, ov::hint::PerformanceMode::LATENCY, "High-level hint that defines target model inference mode. It may impact number of streams, auto batching, etc")
14
14
OV_CONFIG_RELEASE_OPTION(ov::hint, execution_mode, ov::hint::ExecutionMode::PERFORMANCE, "High-level hint that defines the most important metric for the model. Performance mode allows unsafe optimizations that may reduce the model accuracy")
OV_CONFIG_RELEASE_OPTION(ov, cache_mode, ov::CacheMode::OPTIMIZE_SPEED, "Cache mode defines the trade-off between the model compilation time and the disk space required for the cache")
27
27
OV_CONFIG_RELEASE_OPTION(ov, cache_encryption_callbacks, ov::EncryptionCallbacks{}, "Callbacks used to encrypt/decrypt the model")
OV_CONFIG_RELEASE_OPTION(ov, weights_path, "", "Path to the model weights file used for weightless caching")
32
32
OV_CONFIG_RELEASE_OPTION(ov::hint, activations_scale_factor, -1.0f, "Scalar floating point value that is used for runtime activation tensor scaling with fp16 inference precision")
0 commit comments