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

Updated documentation for all classes

Browse source
This commit is contained in:
Alejandro Saucedo 2021-03-06 11:20:09 +00:00
parent 196c896bd6
commit b753660c29
13 changed files with 276 additions and 123 deletions
Download patch file Download diff file Expand all files Collapse all files

23
src/include/kompute/operations/OpTensorCopy.hpp
View file

@ -9,38 +9,47 @@
namespace kp {
/**
Operation that copies the data from the first tensor to the rest of the tensors provided, using a record command for all the vectors. This operation does not own/manage the memory of the tensors passed to it. The operation must only receive tensors of type
* Operation that copies the data from the first tensor to the rest of the tensors
* provided, using a record command for all the vectors. This operation does not
* own/manage the memory of the tensors passed to it. The operation must only
* receive tensors of type
*/
class OpTensorCopy : public OpBase
{
public:
/**
* Default constructor with parameters that provides the core vulkan resources and the tensors that will be used in the operation.
* Default constructor with parameters that provides the core vulkan resources
* and the tensors that will be used in the operation.
*
* @param physicalDevice Vulkan physical device used to find device queues
* @param device Vulkan logical device for passing to Algorithm
* @param commandBuffer Vulkan Command Buffer to record commands into
* @param tensors Tensors that will be used to create in operation.
*/
OpTensorCopy(const std::vector<std::shared_ptr<Tensor>>& tensors);
/**
* Default destructor. This class does not manage memory so it won't be expecting the parent to perform a release.
* Default destructor. This class does not manage memory so it won't be
* expecting the parent to perform a release.
*/
~OpTensorCopy() override;
/**
* Records the copy commands from the first tensor into all the other tensors provided. Also optionally records a barrier.
* Records the copy commands from the first tensor into all the other
* tensors provided. Also optionally records a barrier.
*
* @param commandBuffer The command buffer to record the command into.
*/
void record(const vk::CommandBuffer& commandBuffer) override;
/**
* Does not perform any preEval commands.
*
* @param commandBuffer The command buffer to record the command into.
*/
virtual void preEval(const vk::CommandBuffer& commandBuffer) override;
/**
* Copies the local vectors for all the tensors to sync the data with the gpu.
*
* @param commandBuffer The command buffer to record the command into.
*/
virtual void postEval(const vk::CommandBuffer& commandBuffer) override;