thek0tyara/llama-cpp-turboquant
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions 6

Added functional optensorsyncDevice and optensorsynclocal

Browse source
This commit is contained in:
Alejandro Saucedo 2020-09-06 15:51:31 +01:00
parent e6f4097acb
commit e68d09dbdc
15 changed files with 258 additions and 50 deletions
Download patch file Download diff file Expand all files Collapse all files

12
docs/overview/advanced-examples.rst
View file

@ -121,7 +121,11 @@ Now that we have the inputs and outputs we will be able to use them in the proce
Once we re-record, all the instructions that were recorded previosuly are cleared.
Because of this we can record now the new command which is just the OpAlgoBase with the LR shader.
Because of this we can record now the new commands which will consist of the following:
1. Copy the tensor data from local to device
2. Run the logistic regression shader
3. Copy the output data
.. code-block:: cpp
:linenos:
@ -131,11 +135,15 @@ Because of this we can record now the new command which is just the OpAlgoBase w
sq->begin();
sq->record<kp::OpTensorSyncDevice>({wIn, bIn});
sq->record<kp::OpAlgoBase<>>(
params,
true, // Whether to copy output from device
false, // Whether to copy output from device
"test/shaders/glsl/test_logistic_regression.comp");
sq->record<kp::OpTensorSyncLocal>({wOutI, wOutJ, bOut});
sq->end();
4. Loop across number of iterations + 4-a. Submit algo operation on LR shader