config
Cgml
config | Cgml | |
---|---|---|
4 | 22 | |
33 | 40 | |
- | - | |
8.9 | 8.6 | |
3 days ago | 4 months ago | |
Shell | C++ | |
Apache License 2.0 | GNU Lesser General Public License v3.0 only |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
config
-
AMD Funded a Drop-In CUDA Implementation Built on ROCm: It's Open-Source
https://github.com/ublue-os/config/blob/main/build/ublue-os-...
There's a default `distrobox` with pytorch in ublue-os/config//build/ublue-os-just/etc-distrobox/apps.ini:
- best distro for gaming with proton?
-
Poor native performance in Steam games.
flatpak-system-update.timer.flatpak list | grep Steam ) If it's the flatpak you likely need to run flatpak update -y to get NVidia drivers that match your system. Otherwise you might fall back to software rendering. This command will have to be re-run every time you update your NVidia drivers (After just about every dnf upgrade command). You can have it run automatically with systemd units, see here. (Thanks to the ublue.it team for that btw! ) Just copy those two files into /etc/systemd/system, and run sudo systemctl daemon-reload && sudo systemctl enable
-
uBlue's Nvidia images are now 1.0
We include a bunch of extra udev rules for controllers and other hardware: That container is here specifically if you want to inspect it: https://github.com/ublue-os/config
Cgml
-
Asynchronous Programming in C#
> Meant no offense
None taken.
> computervison project in c#
Yeah, for CV applications nuget.org is indeed not particularly great. Very few people are using C# for these things, people typically choose something else like Python and OpenCV.
BTW, same applies to ML libraries, most folks are using Python/Torch/CUDA stack. For that hobby project https://github.com/Const-me/Cgml/ I had to re-implement the entire tech stack in C#/C++/HLSL.
-
Groq CEO: 'We No Longer Sell Hardware'
> If there is a future with this idea, its gotta be just shipping the LLM with game right?
That might be a nice application for this library of mine: https://github.com/Const-me/Cgml/
That’s an open source Mistral ML model implementation which runs on GPUs (all of them, not just nVidia), takes 4.5GB on disk, uses under 6GB of VRAM, and optimized for interactive single-user use case. Probably fast enough for that application.
You wouldn’t want in-game dialogues with the original model though. Game developers would need to finetune, retrain and/or do something else with these weights and/or my implementation.
-
Ask HN: How to get started with local language models?
If you just want to run Mistral on Windows, you could try my port: https://github.com/Const-me/Cgml/tree/master/Mistral/Mistral...
The setup is relatively easy: install .NET runtime, download 4.5 GB model file from BitTorrent, unpack a small ZIP file and run the EXE.
-
OpenAI postmortem – Unexpected responses from ChatGPT
Speaking about random sampling during inference, most ML models are doing it rather inefficiently.
Here’s a better way: https://github.com/Const-me/Cgml/blob/master/Readme.md#rando...
My HLSL is easily portable to CUDA, which has `__syncthreads` and `atomicInc` intrinsics.
- Nvidia's Chat with RTX is a promising AI chatbot that runs locally on your PC
-
AMD Funded a Drop-In CUDA Implementation Built on ROCm: It's Open-Source
I did a few times with Direct3D 11 compute shaders. Here’s an open-source example: https://github.com/Const-me/Cgml
Pretty sure Vulkan gonna work equally well, at the very least there’s an open source DXVK project which implements D3D11 on top of Vulkan.
-
Brave Leo now uses Mixtral 8x7B as default
Here’s an example of a custom 4 bits/weight codec for ML weights:
https://github.com/Const-me/Cgml/blob/master/Readme.md#bcml1...
llama.cpp does it slightly differently but still, AFAIK their quantized data formats are conceptually similar to my codec.
- Efficient LLM inference solution on Intel GPU
-
Vcc – The Vulkan Clang Compiler
> the API was high-friction due to the shader language, and the glue between shader and CPU
Direct3D 11 compute shaders share these things with Vulkan, yet D3D11 is relatively easy to use. For example, see that library which implements ML-targeted compute shaders for C# with minimal friction: https://github.com/Const-me/Cgml The backend implemented in C++ is rather simple, just binds resources and dispatches these shaders.
I think the main usability issue with Vulkan is API design. Vulkan was only designed with AAA game engines in mind. The developers of these game engines have borderline unlimited budgets, and their requirements are very different from ordinary folks who want to leverage GPU hardware.
-
I made an app that runs Mistral 7B 0.2 LLM locally on iPhone Pros
Minor update https://github.com/Const-me/Cgml/releases/tag/1.1a Can’t edit that comment anymore, too late.
What are some alternatives?
ublue - A familiar(ish) Ubuntu desktop for Fedora Silverblue.
PowerInfer - High-speed Large Language Model Serving on PCs with Consumer-grade GPUs
ostree
ollama - Get up and running with Llama 3, Mistral, Gemma, and other large language models.
silverblue-site - Historic website for Fedora Silverblue. Now at https://gitlab.com/fedora/websites-apps/fedora-websites/fedora-websites-3.0
mlx - MLX: An array framework for Apple silicon
gamemode - Optimise Linux system performance on demand
EmotiVoice - EmotiVoice 😊: a Multi-Voice and Prompt-Controlled TTS Engine
rpm-ostree-toolbox - App for automatically running rpm-ostree, generating disk images
llamafile - Distribute and run LLMs with a single file.
clspv - Clspv is a compiler for OpenCL C to Vulkan compute shaders
HIP - HIP: C++ Heterogeneous-Compute Interface for Portability