//clika-runtime/io.clika.runtime/CompileOptions
CompileOptions
[common]
data class CompileOptions(val inputShapes: Map<String, LongArray> = emptyMap(), val namedDims: Map<String, Long> = emptyMap(), val sampleInputs: Map<String, Tensor> = emptyMap(), val weights: Placement? = null, val stickyWeights: Boolean = false)
How OnnxModel.compile builds the graph. With none of the shape roads a dynamic input dim stays dynamic and the graph binds real shapes at run time; inputShapes pins an input to one fixed shape, namedDims pins every dim declared under that name (an ONNX dim_param), and sampleInputs pins each named input to its example's shape and dtype (the values are never read); the roads combine, the explicit shapes winning. weights is the device or stream the finalized graph serves on (null keeps the operators where they are); stickyWeights keeps the weights resident under memory pressure.
Constructors
| CompileOptions | [common] constructor(inputShapes: Map<String, LongArray> = emptyMap(), namedDims: Map<String, Long> = emptyMap(), sampleInputs: Map<String, Tensor> = emptyMap(), weights: Placement? = null, stickyWeights: Boolean = false) |
Properties
| Name | Summary |
|---|---|
| inputShapes | [common] val inputShapes: Map<String, LongArray> |
| namedDims | [common] val namedDims: Map<String, Long> |
| sampleInputs | [common] val sampleInputs: Map<String, Tensor> |
| stickyWeights | [common] val stickyWeights: Boolean = false |
| weights | [common] val weights: Placement? = null |