MCPcopy Create free account
hub / github.com/UbiquitousLearning/mllm / cacheInputOutputTensor

Method cacheInputOutputTensor

mllm/compile/ir/Node.cpp:266–266  ·  view source on GitHub ↗

Source from the content-addressed store, hash-verified

264}
265
266void IRContext::cacheInputOutputTensor(size_t uuid, const val_ptr_t& tensor_ir) { cached_inputs_outputs_[uuid] = tensor_ir; }
267
268val_ptr_t IRContext::getCacheInputOutputTensor(size_t uuid) { return cached_inputs_outputs_[uuid]; }
269

Callers 1

wrapTensors2TensorIRFunction · 0.80

Calls

no outgoing calls

Tested by

no test coverage detected