CalculonPrime
CalculonPrime
When I make the fixes suggested here for the FP32 GGUF model, then the crash is avoided, but the model doesn't work. It loads fine, I verify that the template...
> I only tested 120B FP16 GGUF file and it works fine. I reported the same in the post you quoted. > > From what I can see, the problem...
Looks like this is caused by a deadlock in the error output stream from the underlying llama cpp process. I tried to debug the issue by making this change to[...
Should I apply all of your suggested changes and then resubmit the pull request?
OK. ChatGPT said to just update the branch from which I submitted the pull request, so I've [made that update](https://github.com/CalculonPrime/my-windhawk-mods/commits/main/mods/taskbar-on-top.wh.cpp).
Let me know if I need to take some additional action before this change can be added to the release.