Comments (4)
I see no reasons it doesn't do well in the CV world,
Sure, what I meant was convolution operations in GGML currently have fixed kernel sizes / strides. We need to figure out a way of implementing generic convolutions, then implementing any convolution-based model should be straightforward. Luckily, ViT models usually use a single type of convolution operation and the rest is plain transformer blocks. But traditional models such as ResNet have a very rich set of convolution ops.
Do you have any local test data avaialble on the inference speed comparison between torch&CUDA vs clip.cpp
I implemented a benchmarking utility to measure the zero-shot labeling performance with acc@1 and acc@5 metrics as well as inference time, but haven't done a full comparison with Pytorch --I'm trying to decide on a good test set. I'm also currently working on batch inference support, maybe it would be more appropriate to include single-instance and batch inference performances in benchmarking.
from clip.cpp.
Unfortunately not yet. Currently this implements only ViT architecture. GGML's support for convolutions is currently limited, and as I implement more models I'd like to contribute back to GGML. I have a few architectures in mind to implement after CLIP, but community demand is also important.
from clip.cpp.
Thanks.
I think ggml is proven to be very efficient in the LLM inference, I see no reasons it doesn't do well in the CV world, plus the quantization is quite handy. k-quant is even better yet that's specific to transformers.
Do you have any local test data avaialble on the inference speed comparison between torch&CUDA vs clip.cpp &cuBLAS on the same ViT architecture?
from clip.cpp.
Unfortunately not yet. Currently this implements only ViT architecture. GGML's support for convolutions is currently limited, and as I implement more models I'd like to contribute back to GGML. I have a few architectures in mind to implement after CLIP, but community demand is also important.
so,How's it going now?How's it going now?I came here from stable diffusion.cpp, ggml_conv_2d caused sd to not run on gpu.Its optimization needs some inspiration
from clip.cpp.
Related Issues (20)
- python binding: OSError libggml.so: cannot open shared object file HOT 4
- Migrate to GGUF 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.