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

Updated to use all uint32_t to avoid ambiguity on passing strings

Browse source
This commit is contained in:
Alejandro Saucedo 2021-02-20 18:09:02 +00:00
parent 5bc3ac9c06
commit 56d9a3a933
18 changed files with 65 additions and 68 deletions
Download patch file Download diff file Expand all files Collapse all files

4
src/include/kompute/Algorithm.hpp
View file

@ -39,7 +39,7 @@ public:
* @specalizationInstalces The specialization parameters to pass to the function
* processing
*/
void init(const std::vector<char>& shaderFileData,
void init(const std::vector<uint32_t>& shaderFileData,
std::vector<std::shared_ptr<Tensor>> tensorParams);
/**
@ -83,7 +83,7 @@ private:
Constants mSpecializationConstants;
// Create util functions
void createShaderModule(const std::vector<char>& shaderFileData);
void createShaderModule(const std::vector<uint32_t>& shaderFileData);
void createPipeline();
// Parameters