Comments (8)
Memory issue will be handled in #8, and I'll have a look at the other crash.
from clip.cpp.
I had an oh! moment just wen pouring coffee into my cup :D Instead of hardcoding a single memory size or running a warmup just to learn the memory requirement, we can decide based on the number of tensors, which essentially indicates the model size. So it sounds like an overengineering, but it's not --it's the only way of automatically setting the correct memory size without any initial delay or lib user's intervention, or the only way I could come up with.
from clip.cpp.
Yeah, but I checked out the fixing branch from my fork until then. We can checkout the upstream master again once it's merged.
from clip.cpp.
Reproduced the issue. Will patch it after testing with other checkpoints of models.
from clip.cpp.
I think this relates to ggerganov/ggml#260
from clip.cpp.
Yes, so let's think of it as a workaround until the proper mecanism is implemented in GGML.
I pushed it in #11
I think we can already merge it.
- the memory is allocated based on the model variant.
- the NaN issue is resolved for larger models with the patch size of 14.
from clip.cpp.
nice. yea, it's been an issue ever since i started with llama.cpp 😆
to 2. , you mean one ggerganov/ggml#274 is merged?
from clip.cpp.
from clip.cpp.
Related Issues (20)
- Support custom mean-std normalization HOT 3
- not enough space in the context's memory pool (on Apple M1 Max, 32GB RAM, clip-vit-b-32) HOT 6
- Provide Python bindings
- [ZSL] Results doesn't match hugging face demo HOT 5
- Segmentation Fault and Core Dump when running image-search-build with Multiple images in folder Using the 4bit model HOT 5
- Publish as a Pip-installable Python package HOT 1
- Improve zero-shot labeling
- 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
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.