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

Updated to remove all todos

Browse source
This commit is contained in:
Alejandro Saucedo 2020-09-02 21:25:30 +01:00
parent af4f429d4d
commit 07bfbe3504
9 changed files with 20 additions and 39 deletions
Download patch file Download diff file Expand all files Collapse all files

13
src/include/kompute/Tensor.hpp
View file

@ -68,9 +68,18 @@ class Tensor
* important to ensure that there is no out-of-sync data with the GPU
* memory.
*
* @return Vector of elements representing the data in the tensor.
* @return Reference to vector of elements representing the data in the tensor.
*/
std::vector<float> data();
std::vector<float>& data();
/**
* Overrides the subscript operator to expose the underlying data's
* subscript operator which in this case would be its underlying
* vector's.
*
* @param i The index where the element will be returned from.
* @return Returns the element in the position requested.
*/
float& operator[] (int index);
/**
* Returns the size/magnitude of the Tensor, which will be the total number
* of elements across all dimensions