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

Added to changelog

Browse source 
Signed-off-by: Alejandro Saucedo <axsauze@gmail.com>
This commit is contained in:
Alejandro Saucedo 2021-09-12 19:34:50 +01:00
parent 1b0159e02c
commit 21d9939c2d
2 changed files with 8 additions and 5 deletions
Download patch file Download diff file Expand all files Collapse all files

6
docs/overview/matmul-benchmark.rst
View file

@ -3,10 +3,12 @@
Implementation Overview
================
---------
The benchmark can be found in the `benchmark.py` file in the repo, which is outlined below. This file runs a naive implementation of the three matrix multiplication implementations to evaluate the performance of each.
.. literalinclude:: ../../examples/python_naive_matmuln/benchmark.py
.. literalinclude:: ../../examples/python_naive_matmul/benchmark.py
:language: python

7
examples/neural_network_vgg7/README.md
View file

@ -30,11 +30,11 @@ We implement the kompute logic under run_vgg7 that loads the model weights and c
Similarly, we created a compute shader that performs an inference iteration on an image provided to perfrom upscaling.
## run model against image to perfrom upscale
## Run model against image to perfrom upscale
We now execute model against an image created by us to show how upscaling works. The image used will be the one below:
![](w2wbinit.png)
![](https://raw.githubusercontent.com/KomputeProject/kompute/master/examples/neural_network_vgg7/w2wbinit.png)
To execute that model no tiling is performed, so be careful about image sizes.
@ -44,5 +44,6 @@ We can now run the command below to perform inference against the image blow.
This would successfully upscale the resolution using the machine learning model, and the result is below:
![](out.png)
![](https://raw.githubusercontent.com/KomputeProject/kompute/master/examples/neural_network_vgg7/out.png)