OptionalactiveA list of LoRA adapters to activate for this run. See LoraAdapter.
The adapters must be created by the same backend as the session. Parameters of different adapters that are active at the same time must not overlap.
This setting is available only in WebAssembly backend. It is not supported yet in proxy mode
(env.wasm.proxy), or for a session that uses IO binding. IO binding is used when an output is preferred to be
on GPU (see SessionOptions.preferredOutputLocation), when graph capture is enabled, and in some cases with the
WebNN execution provider.
OptionalextraSet a single run configuration entry. See https://github.com/microsoft/onnxruntime/blob/main/include/onnxruntime/core/session/ onnxruntime_run_options_config_keys.h
This setting is available only in WebAssembly backend. Will support Node.js binding and react-native later
OptionallogLog severity level. See https://github.com/microsoft/onnxruntime/blob/main/include/onnxruntime/core/common/logging/severity.h
This setting is available only in ONNXRuntime (Node.js binding and react-native) or WebAssembly backend
OptionallogLog verbosity level.
This setting is available only in WebAssembly backend. Will support Node.js binding and react-native later
OptionaltagA tag for the Run() calls using this
This setting is available only in ONNXRuntime (Node.js binding and react-native) or WebAssembly backend
OptionalterminateTerminate all incomplete OrtRun calls as soon as possible if true
This setting is available only in WebAssembly backend. Will support Node.js binding and react-native later
A set of configurations for inference run behavior