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

Added initial implementation for algorithm and opMult

Browse source
This commit is contained in:
Alejandro Saucedo 2020-08-21 19:15:07 +01:00
parent 0d18dc50e6
commit d59dc41ffc
11 changed files with 385 additions and 28 deletions
Download patch file Download diff file Expand all files Collapse all files

10
src/OpMult.hpp
View file

@ -11,6 +11,7 @@
#include <spdlog/spdlog.h>
#include "Tensor.hpp"
#include "Algorithm.hpp"
#include "OpBase.hpp"
@ -31,9 +32,14 @@ class OpMult : public OpBase
void record() override;
void postSubmit() override;
private:
std::shared_ptr<Tensor> mPrimaryTensor;
std::shared_ptr<Tensor> mStagingTensor;
Algorithm mAlgorithm;
std::shared_ptr<Tensor> mTensorLHS;
std::shared_ptr<Tensor> mTensorRHS;
std::shared_ptr<Tensor> mTensorOutput;
std::shared_ptr<Tensor> mTensorOutputStaging;
};
} // End namespace kp