holoscan::utils::TensorTransmitCache

Beta

Persistent cache for output message and tensor allocations used by the cached variant of transmit_data_per_model.

Holds a reusable GXF entity and per-tensor metadata to minimise per-frame overhead. Three cases are handled each frame:

First use or buffer too small: full reshape (reallocate + update shape).
Incoming fits in existing allocation but dims changed: wrapMemory to update shape metadata only — no free/alloc of the underlying buffer.
Same dims as last frame: fast path, no tensor mutation at all.

#include <holoscan/utils/holoinfer_utils.hpp>

Member variables

Name	Type	Description
`out_message`	`nvidia::gxf::Expected< nvidia::gxf::Entity >`	Persistent output entity. Invalid (falsy) until the first call to transmit_data_per_model.
`allocated_sizes`	`std::map< std::string, size_t >`	Maximum element count that has been allocated for each output tensor.
`last_dims`	`std::map< std::string, std::vector< int64_t > >`	Dimension vector from the most recent frame for each output tensor, used to detect shape changes that require a wrapMemory call even when the element count has not grown.