Iván Baldo comments

Results 33 comments of


                                            Iván Baldo

panic without nvidia-smi

`CUDA_COMPUTE_CAP=all` would be nice to have, for example to build generic container images that could run on any hardware.

Doesn't prioritize requests and doesn't have fairness with LVM/DeviceMapper

Hello. Don't worry, we both are busy, I know how it is. Now with Kernel 5.11 it's better, it works perfectly for reads, at least O_DIRECT ones in Ext4 with...

Doesn't prioritize requests and doesn't have fairness with LVM/DeviceMapper

Now with kernel 5.15 I can't reproduce the issue anymore, thanks a lot!

Doesn't prioritize requests and doesn't have fairness with LVM/DeviceMapper

Doh I was running the command wrongly, the one for idle was running like this: ``` while ionice -c3 dd if=/dev/zero of=delete1 status=progress oflag=direct; bs=1M count=1000; do true; done ```...

What's the use of pm_type=1 when mptcpd manipulates the ip mptcp endpoint table anyway? And whitelist interfaces request.

So this seems to be a documentation issue then. Because I don't see the plugins properly documented and clarifying which sysctl setting they need.

There still is VRAM estimation issue in 0.9.0 version

Thanks a lot for your work on this @jessegross , well done!!!

feat: Handling of a large number of knowledge base files

Three weeks and no clarification, should be clarified or closed...

Is this project abandoned?

Does anyone know of any good (healthy) fork or alternative?

[Feature Request] Support for Local AI Backends (e.g., Ollama, LocalAI)

Isn't this implemented already? Shouldn't this issue be closed now?

ollama run phi4-min does not work

@ssdeepak does it work now? Please close the issue if fixed, thanks!!