clika_runtime.io

Model files and media in and out.

Checkpoints load as a dict of tensors (:func:load_safetensors, :func:load_torch_checkpoint, :func:load_gguf) or open as a :class:TensorsContainer whose entries read from disk on first use (:func:open_safetensors, :func:open_torch_checkpoint, :func:open_gguf, or :meth:TensorsContainer.open by file suffix). A safetensors file's own order and its metadata read back through :func:load_safetensors_entries (a :class:SafetensorsEntries: the (name, tensor) pairs in header order and the metadata as string pairs), and :func:save_safetensors writes its entries in the given order with optional metadata. ONNX models open as an editable :class:OnnxModel and compile into a runnable :class:ModelGraph; :mod:clika_runtime.onnx is the one-call loader over them. The audio pair decodes and writes waveforms; the npy pair moves one tensor.

Name	Kind
BenchOptions	class
BenchReport	class
ContainerEntry	class
DimDomain	class
FeedFill	class
InputShape	class
KVCacheLayerInfo	class
ModelGraph	class
OnnxModel	class
OnnxNodeInfo	class
SafetensorsEntries	class
ShapeDomain	class
TensorsContainer	class
functions	module functions