Sławomir Gajowniczek
Sławomir Gajowniczek
One thing to consider in general 3.13 release. Default Python 3.13 has similar behaviour like 3.12 however there is new 3.13t version that has changes to GIL (threading mechanism). If...
@callahad That is what I wanted to say - GIL is a experimental build so don't bother to include it in a Unit supported at the moment. That will come...
Dot is fine i gues. Also the use case is that i have a list of dates/times and i want to mark them Past/Future/Now. Where for now none of existing...
[win_x64.log](https://github.com/user-attachments/files/16399105/win_x64.log)
Sorry I was wrong. That is not happening on linux. My LiteLLM is doing some load-balancing and I thought that went to linux nodes. But there is also a `segmentation...
I've re-uploaded it. `time=2024-07-27T14:04:05.563+02:00 level=ERROR source=sched.go:443 msg="error loading llama server" error="llama runner process has terminated: signal: segmentation fault"`
[ollama_llama_server-2024-07-27-140405.txt](https://github.com/user-attachments/files/16400221/ollama_llama_server-2024-07-27-140405.txt) Changed the extension to .txt
I will raise a llama.cpp ticket. I understand there is different root cause for each.
I had similar issues both on my Intel Mac and Apple Silicon. I noticed the problem is when there is a connection issue. For example after sleep etc. Also once...
I can confirm that latest 2024.4 (2024.624) still has an issue. It happens for me when the Companion App was connected to the HA service, disconnect my MacBook from the...