Eric Curtin
Eric Curtin
@Yarboa reported this is not working on this kind of image. We must debug and figure this out.
In Fedora/CentOS Stream 9, /boot will be vfat or ext4 (there is talk of unifying /boot/efi and /boot into one partition in Fedora, a vfat one, vfat is mandatory for...
This might just work, but it needs to be tested. In Fedora there is talk about /boot and /boot/efi partitions being merged as a single vfat /boot partition, so lets...
Split these into two different binaries we two different resonsibilities. They don't share so much functionality.
### Prerequisites - [X] I am running the latest code. Mention the version if possible as well. - [X] I carefully followed the [README.md](https://github.com/ggerganov/llama.cpp/blob/master/README.md). - [X] I searched using keywords...
**Is your feature request related to a problem? Please describe.** Ollama has an easy to use repo, you can pull via short and simple strings. **Describe the solution you'd like**...
Just a piece of random feedback but if we want to be more crun/runc/krun-like (I think we should by default), if we can edit a couple of files in the...
As you can see from the curl commands below from the ramalama project (toggle x = True in the ramalama python script to print the curl commands) the "Accept: application/vnd.docker.distribution.manifest.v2+json"...
**Is your feature request related to a problem? Please describe.** Serverless inferencing is possible with llama.cpp via llama-cli, for example one can do something like this: llama-cli -m /home/curtine/.local/share/ramalama/models/ollama/granite-code:latest --log-disable...