Comments (5)
When the TensorSplitsCollection
is created it runs this code:
internal readonly float[] Splits = new float[NativeApi.llama_max_devices()];
If you just try to execute that, does it crash in the same way?
from llamasharp.
I'm only using the nuget package right now on my notebook and can't edit the llamasharp code. But I tried calling NativeApi.llama_max_devices() in my code directly and the same thing happens. The debugger aborts. It seems, that llama_max_devices can't be callen on my notebook .
from llamasharp.
The NativeApi call just directly calls llama.cpp and there's no other C# code involved, so I think you'll have to report this one to llama.cpp.
from llamasharp.
I went to look at llama.cpp and the contents of llama_max_devices
are:
int llama_max_devices(void) {
return LLAMA_MAX_DEVICES;
}
So there's probably something else going wrong here!
from llamasharp.
I currently have looked at the ModelParams method on PC and notebook in the debugger. Somehow this method looks different. On the PC the constructor looks like this.
But on the notebook the constructor looks like this
I'm actually using the same GIT status on both pcs. If the constructor on the notebook and PC were swapped, it probably wouldn't crash when calling llama_max_devices, because my PC has no problems with this method. But I don't understand why the constructor looks different at all. Maybe I'll see a bit clearer tomorrow^^.
EDIT:
Oh man. I'm really sorry. I figured it out. I tested on both PCs with the same Settings (avx2). But my notebook only supports avx. This was my mistake.
from llamasharp.
Related Issues (20)
- CentOS x86_64 Failed Loading 'libllama.so' HOT 4
- System.TypeInitializationException: 'The type initializer for 'LLama.Native.NativeApi' threw an exception.' HOT 12
- How do I continously print the answer word for word when using document ingestion with kernel memory? HOT 1
- How to rebuild LLamaSharp backends HOT 3
- Namespace should be consistent HOT 2
- Mamba HOT 11
- Android Backend HOT 5
- [Feature] Allow async model loading and cancellation
- [CI] Add more unit test to ensure the the outputs are reasonable HOT 3
- Take multiple chat templates into account
- [Feature]: Support for Function Calling or Tools HOT 4
- [BUG]: DefragThreshold default is not matching llama.cpp and probably not intended HOT 6
- [BUG]: Answer stop abruptly after contextsize, even with limiting prompt size HOT 1
- [BUG]: Linux cuda version detection could be incorrect HOT 2
- [BUG]: WSL2 has problem running LLamaSharp with cuda11
- Add unit test about long context HOT 3
- Add debug mode of LLamaSharp
- How to better provide system information for LLMs HOT 3
- LLAVA Configuration HOT 4
- [Feature]: 不同的LLM模型,代码要以怎样的方式融合到项目里 HOT 3
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 llamasharp.