![](https://feditown.com/pictrs/image/b12b9481-e519-4ef5-892b-08587c2257fc.webp)
![](https://lemmy.world/pictrs/image/8286e071-7449-4413-a084-1eb5242e2cf4.png)
I don’t know of any project that already supports that AI processor. You’d still be using the CPU and GPU at the moment.
I don’t know of any project that already supports that AI processor. You’d still be using the CPU and GPU at the moment.
I can really recommend XCP-ng. For me it strikes a pretty good balance of features and ease of use.
Using whatever works better for the current project is doing Hybrid Cloud. Now your boss can brag about how modern the infrastructure is.
And 2d, who self host on a server/VPS they rented somewhere.
ISPs were already required to block the sites. I don’t think an additional block on the Cisco side would change anything in that case.
Apparently Cisco operates a popular DNS resolver? Never heard of that before.
And definitely don’t learn how to use a VPN. Or set up Unbound or Bind or PowerDNS Recursive…
KDEConnect?
deleted by creator
Maybe check out Tailscale. It’s mainly a mesh VPN for your own devices, but they have a lot of options included so you can share stuff with other people.
You can install Wireguard or another VPN to encrypt your traffic to the VPS.
You’ll want to install a reverse proxy of your choice on the VPS. Have clients access it over ipv4 and configure it to proxy pass it to your ipv6 address. Nginx at least is capable of doing ipv4 & ipv6 -> ipv4, I think the inverse should also be possible.
You can use OpenCL instead of ROCm for GPU offloading. In my tests with llama.cpp that improved performance massively.
Definitely do benchmarks for how many layers you can offload to the GPU. You’ll see when it’s too many, as performance will crater.
By launching llama.cpp as a server you’ll actually be able to continue to use openwebui as you currently have.
It would probably take someone to sue them, but they would have to implement it.
It’s probably still more efficient to keep a 192k opus and a 320k mp3 around than one flac.
Yeah, they’re more power hungry, but they’re also way more performant than a pi 4.
VAAPI is the “standard” interface for hardware en-/decoding on Linux. It should work with any GPU using the open source drivers and mesa.
I don’t know how QSV can be installed; AMF, the AMD equivalent, is limited to their proprietary driver.
On my phone (Android, LineageOS) there’s an option in the hotspot settings to allow clients to use the active VPN.
Besides maybe confusing the codecs, hardware encoders, especially the AMD ones, are always less space efficient than software encoders.
If you want to convert video for long-term storage, please use a software encoder.
I recently found out about Softwareheritage, they also have yuzu mirrored.
Get a cheap VPS and set up a VPN of your choice.