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

Uplaoded python package to pypi

Browse source
This commit is contained in:
Alejandro Saucedo 2020-11-04 20:58:05 +00:00
parent 68028420cb
commit 04e9a24705
3 changed files with 34 additions and 23 deletions
Download patch file Download diff file Expand all files Collapse all files

6
MANIFEST.in Normal file
View file

@ -0,0 +1,6 @@
include CMakeLists.txt
recursive-include src *
recursive-include python *
recursive-include single_include *
recursive-include external *

38
README.md
View file

@ -179,6 +179,25 @@ static std::string shaderData = "path/to/shader.glsl";
static std::string shaderData = "path/to/shader.glsl.spv";
```
## More examples
### Simple examples
* [Pass shader as raw string](https://kompute.cc/overview/advanced-examples.html#simple-shader-example)
* [Record batch commands with a Kompute Sequence](https://kompute.cc/overview/advanced-examples.html#record-batch-commands)
* [Run Asynchronous Operations](https://kompute.cc/overview/advanced-examples.html#asynchronous-operations)
* [Run Parallel Operations Across Multiple GPU Queues](https://kompute.cc/overview/advanced-examples.html#parallel-operations)
* [Create your custom Kompute Operations](https://kompute.cc/overview/advanced-examples.html#your-custom-kompute-operation)
* [Implementing logistic regression from scratch](https://kompute.cc/overview/advanced-examples.html#logistic-regression-example)
### End-to-end examples
* [Machine Learning Logistic Regression Implementation](https://towardsdatascience.com/machine-learning-and-data-processing-in-the-gpu-with-vulkan-kompute-c9350e5e5d3a)
* [Parallelizing GPU-intensive Workloads via Multi-Queue Operations](https://towardsdatascience.com/parallelizing-heavy-gpu-workloads-via-multi-queue-operations-50a38b15a1dc)
* [Android NDK Mobile Kompute ML Application](https://towardsdatascience.com/gpu-accelerated-machine-learning-in-your-mobile-applications-using-the-android-ndk-vulkan-kompute-1e9da37b7617)
* [Game Development Kompute ML in Godot Engine](https://towardsdatascience.com/supercharging-game-development-with-gpu-accelerated-ml-using-vulkan-kompute-the-godot-game-engine-4e75a84ea9f0)
## Architectural Overview
The core architecture of Kompute includes the following:
@ -329,25 +348,6 @@ assert tensor_out.data() == [2.0, 4.0, 6.0]
For further details you can read the [Python Package documentation](https://kompute.cc/overview/python-package.html) or the [Python Class Reference documentation](https://kompute.cc/overview/python-reference.html).
## More examples
### Simple examples
* [Pass shader as raw string](https://kompute.cc/overview/advanced-examples.html#simple-shader-example)
* [Record batch commands with a Kompute Sequence](https://kompute.cc/overview/advanced-examples.html#record-batch-commands)
* [Run Asynchronous Operations](https://kompute.cc/overview/advanced-examples.html#asynchronous-operations)
* [Run Parallel Operations Across Multiple GPU Queues](https://kompute.cc/overview/advanced-examples.html#parallel-operations)
* [Create your custom Kompute Operations](https://kompute.cc/overview/advanced-examples.html#your-custom-kompute-operation)
* [Implementing logistic regression from scratch](https://kompute.cc/overview/advanced-examples.html#logistic-regression-example)
### End-to-end examples
* [Machine Learning Logistic Regression Implementation](https://towardsdatascience.com/machine-learning-and-data-processing-in-the-gpu-with-vulkan-kompute-c9350e5e5d3a)
* [Parallelizing GPU-intensive Workloads via Multi-Queue Operations](https://towardsdatascience.com/parallelizing-heavy-gpu-workloads-via-multi-queue-operations-50a38b15a1dc)
* [Android NDK Mobile Kompute ML Application](https://towardsdatascience.com/gpu-accelerated-machine-learning-in-your-mobile-applications-using-the-android-ndk-vulkan-kompute-1e9da37b7617)
* [Game Development Kompute ML in Godot Engine](https://towardsdatascience.com/supercharging-game-development-with-gpu-accelerated-ml-using-vulkan-kompute-the-godot-game-engine-4e75a84ea9f0)
## Build Overview
The build system provided uses `cmake`, which allows for cross platform builds.

13
setup.py
View file

@ -8,6 +8,9 @@ from setuptools import setup, Extension
from setuptools.command.build_ext import build_ext
from distutils.version import LooseVersion
curr_dir = os.path.abspath(os.path.dirname(__file__))
with open(os.path.join(curr_dir, 'README.md'), encoding='utf-8') as f:
long_description = f.read()
class CMakeExtension(Extension):
def __init__(self, name, sourcedir=''):
@ -46,13 +49,13 @@ class CMakeBuild(build_ext):
build_args = ['--config', cfg]
if platform.system() == "Windows":
cmake_args += ['-DKOMPUTE_EXTRA_CXX_FLAGS="-DSPDLOG_ACTIVE_LEVEL=0"']
cmake_args += ['-DKOMPUTE_EXTRA_CXX_FLAGS=""']
cmake_args += ['-DCMAKE_LIBRARY_OUTPUT_DIRECTORY_{}={}'.format(cfg.upper(), extdir)]
if sys.maxsize > 2**32:
cmake_args += ['-A', 'x64']
build_args += ['--', '/m']
else:
cmake_args += ['-DKOMPUTE_EXTRA_CXX_FLAGS="-fPIC -DSPDLOG_ACTIVE_LEVEL=0"']
cmake_args += ['-DKOMPUTE_EXTRA_CXX_FLAGS="-fPIC"']
cmake_args += ['-DCMAKE_BUILD_TYPE=' + cfg]
build_args += ['--', '-j2']
@ -67,11 +70,13 @@ class CMakeBuild(build_ext):
setup(
name='kp',
version='0.0.1',
version='0.4.1',
author='Alejandro Saucedo',
description='Vulkan Kompute: Blazing fast, mobile-enabled, asynchronous, and optimized for advanced GPU processing usecases.',
long_description='',
long_description=long_description,
long_description_content_type='text/markdown',
ext_modules=[CMakeExtension('kp')],
cmdclass=dict(build_ext=CMakeBuild),
zip_safe=False,
include_package_data=True,
)