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

Updated readme

Browse source
This commit is contained in:
Alejandro Saucedo 2020-10-25 08:08:23 +00:00
parent 43c7b89d40
commit 926c71581a
1 changed files with 6 additions and 6 deletions
Download patch file Download diff file Expand all files Collapse all files

12
README.md
View file

@ -164,7 +164,7 @@ Simplified Kompute Components
Kompute provides flexibility to run operations in an asynrchonous way through Vulkan Fences. Furthermore, Kompute enables for explicit allocation of queues, which allow for parallel execution of operations across queue families.
The image below provides an intuition how Kompute Sequences can be allocated to different queues to enable parallel execution based on hardware. You can see the [hands on example](https://kompute.cc/overview/advanced-examples.html#parallel-operations), as well as the [detailed documentation page](https://kompute.cc/overview/async-parallel.html) describing how it would work using an NVIDIA 1650 as example.
The image below provides an intuition on how Kompute Sequences can be allocated to different queues to enable parallel execution based on hardware. You can see the [hands on example](https://kompute.cc/overview/advanced-examples.html#parallel-operations), as well as the [detailed documentation page](https://kompute.cc/overview/async-parallel.html) describing how it would work using an NVIDIA 1650 as an example.
![](https://raw.githubusercontent.com/ethicalml/vulkan-kompute/master/docs/images/queue-allocation.jpg)
@ -179,7 +179,7 @@ Kompute has been optimized to work in mobile environments. The [build system](#b
<p>
For a full deep dive you can read the blog post "<a href="https://towardsdatascience.com/gpu-accelerated-machine-learning-in-your-mobile-applications-using-the-android-ndk-vulkan-kompute-1e9da37b7617">Supercharging your Mobile Apps with On-Device GPU Accelerated Machine Learning</a>".
You can also access the <a href="https://github.com/EthicalML/vulkan-kompute/tree/v0.4.0/examples/android/android-simple">end-to-end example code</a> in the repository - this example provides an end to end example that can be run using android studio.
You can also access the <a href="https://github.com/EthicalML/vulkan-kompute/tree/v0.4.0/examples/android/android-simple">end-to-end example code</a> in the repository, which can be run using android studio.
</p>
@ -198,9 +198,9 @@ You can also access the <a href="https://github.com/EthicalML/vulkan-kompute/tre
## Motivations
This project started after seeing that a lot of new and renowned ML & DL projects like Pytorch, Tensorflow, Alibaba DNN, between others, have either integrated or are looking to integrate the Vulkan SDK to add mobile (and cross-vendor) GPU support.
This project started after seeing that a lot of new and renowned ML & DL projects like Pytorch, Tensorflow, Alibaba DNN, Tencent NCNN - among others - have either integrated or are looking to integrate the Vulkan SDK to add mobile (and cross-vendor) GPU support.
The Vulkan SDK offers a great low level interface that enables for highly specialized optimizations - however it comes at a cost of highly verbose code which requires 500-2000 lines of code to even begin writing application code. This has resulted in each of these projects having to implement the same baseline to abstract the non-compute related features of Vulkan. This large amount of non-standardised boiler-plate can result in limited knowledge transfer, higher chance of unique framework implementation bugs being introduced, between others.
The Vulkan SDK offers a great low level interface that enables for highly specialized optimizations - however it comes at a cost of highly verbose code which requires 500-2000 lines of code to even begin writing application code. This has resulted in each of these projects having to implement the same baseline to abstract the non-compute related features of Vulkan. This large amount of non-standardised boiler-plate can result in limited knowledge transfer, higher chance of unique framework implementation bugs being introduced, etc.
We are currently developing Vulkan Kompute not to hide the Vulkan SDK interface (as it's incredibly well designed) but to augment it with a direct focus on Vulkan's GPU computing capabilities. [This article](https://towardsdatascience.com/machine-learning-and-data-processing-in-the-gpu-with-vulkan-kompute-c9350e5e5d3a) provides a high level overview of the motivations of Kompute, together with a set of hands on examples that introduce both GPU computing as well as the core Vulkan Kompute architecture.
@ -372,9 +372,9 @@ We appreciate PRs and Issues. If you want to contribute try checking the "Good f
##### Updating documentation
To update the documentation will need to:
To update the documentation you will need to:
* Run the gendoxygen target in the build system
* Run the gensphynx target in the buildsystem
* Run the gensphynx target in the build-system
* Push to github pages with `make push_docs_to_ghpages`
##### Running tests