Comments (4)
Hi @monatis! Someone over at www.github.com/leejet/stable-diffusion.cpp suggested that maybe you’d want to help enable GPU acceleration for that repo. Would you be interested?
Sorry to ping you in this thread, but don’t know how else to get in touch!
from clip.cpp.
Hi @Happenedtostumblein thanks for reaching out!. GPU support requires to implement conv2d op for CUDA that would be something clip.cpp also benefits from. It's in my TODO list, but the time I can devote to these projects may be limited from time to time due to contractual work I'm doing to make some money. I still hope to devote more time to accelerate development of these projects.
from clip.cpp.
Hey Yusif!
Would you mind elaborating on what exactly makes it time-consuming or is merely outlining the work laborious in itself?
If you’re able to provide me with a 1,2,3 list of steps and goals, perhaps I can do it. I’m pretty good with numbers and math, but don’t speak cpp.
If it’s just not that simple, please excuse my ignorance and thank you again for your time and contributions :)
from clip.cpp.
@Happenedtostumblein Programming for CUDA requires you to know how to parallelize calculations, implement a kernel for conv2d, and, above all, support different data types (quantized and full integers).
from clip.cpp.
Related Issues (20)
- python binding: OSError libggml.so: cannot open shared object file HOT 4
- Move ZSL implementation to `clip` lib as a function
- Support downloading models in Python bindings HOT 1
- Introduce Java bindings
- Support batch inference for models other than patch32 HOT 3
- python bindings🐍: Support for accepting list of Input in the encoding methods HOT 7
- Implement bicubic interpolation
- Can u please make exe of this project? HOT 2
- no module named 'gguf' HOT 2
- Metal support? HOT 5
- Building with -DCLIP_BUILD_IMAGE_SEARCH=ON for image-search fails, ‘cos_gt’ is not a member of ‘unum::usearch’ HOT 4
- Vision only model memory issue
- Slower image encode the lower the quantization HOT 1
- Memory leak: clip_tokenize and clip_image_preprocess
- Question about the CLIP model in clip.cpp and llama.cpp HOT 1
- include clip.cpp in another project
- Python Bindings, optionally pass PIL image
- Python Bindings distributions for different architectures
- Python Binding Example: AttributeError: dlsym(0x8ea2fac0, make_clip_image_u8): symbol not found HOT 4
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from clip.cpp.