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

Updated tests to align with new sequence memory management workflow

Browse source
This commit is contained in:
Alejandro Saucedo 2020-11-01 20:25:53 +00:00
parent 473031d1f3
commit e2f6e876bc
4 changed files with 54 additions and 46 deletions
Download patch file Download diff file Expand all files Collapse all files

2
test/TestTensor.cpp
View file

@ -24,7 +24,7 @@ TEST(TestTensor, CopyFromHostData)
kp::Manager mgr;
if (std::shared_ptr<kp::Sequence> sq =
mgr.getOrCreateManagedSequence("new").lock()) {
mgr.getOrCreateManagedSequence("new")) {
sq->begin();
sq->record<kp::OpTensorCreate>({ tensorA, tensorB });