thek0tyara/llama-cpp-turboquant
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions 4

Added functional optensorsyncDevice and optensorsynclocal

Browse source
This commit is contained in:
Alejandro Saucedo 2020-09-06 15:51:31 +01:00
parent e6f4097acb
commit e68d09dbdc
15 changed files with 258 additions and 50 deletions
Download patch file Download diff file Expand all files Collapse all files

10
src/OpTensorCopy.cpp
View file

@ -57,9 +57,15 @@ OpTensorCopy::record()
}
void
OpTensorCopy::postSubmit()
OpTensorCopy::preEval()
{
SPDLOG_DEBUG("Kompute OpTensorCopy postSubmit called");
SPDLOG_DEBUG("Kompute OpTensorCopy preEval called");
}
void
OpTensorCopy::postEval()
{
SPDLOG_DEBUG("Kompute OpTensorCopy postEval called");
// Copy the data from the first tensor into all the tensors
for (size_t i = 1; i < this->mTensors.size(); i++) {