Eric Curtin

``` $ ls -Z /usr/bin/ostree system_u:object_r:install_exec_t:s0 /usr/bin/ostree ``` ``` env RUST_LOG=debug bootc switch --transport containers-storage e6293f73bcc3 DEBUG argv0=None DEBUG Re-executing current process for _ostree_unshared DEBUG argv0=Some("bootc") DEBUG Already in a...

Was chatting to @carlwgeorge and we think it makes sense to change the primary name of the package to be the application/executable name and make python3-ramalama be an alias. Looping...

ramalama would be a better primary name @smooge but I trust your judgement

We should loop in @mairin @r0x0d etc. here

@r0x0d Just enhance the client code in RamaLama to talk to the lightspeed endpoint, it's just another openai endpoint at the end of the day, a reference implementation is here:...

@slp if you can rebase slp/mesa to be on top of latest mesa in rawhide, we can eliminate the asahi image. Since mesa 25.1 the asahi patches are merged.

We can eliminate the Asahi container image in two ways... 1. @slp rebases his copr we are using, on top of the version of mesa currently available in rawhide (includes...

It's on, we still need @slp 's patches upstream, so eventually Asahi and all this can be consolidate, closing for now though will take a while

I am finished this PR today: https://github.com/containers/ramalama/pull/1068 which will add a llama-server-core wrapper script that is the first executed thing in the container. This wrapper script should query the accelerators...

Python3 implementation: https://github.com/ericcurtin/lm-pull/blob/f688fb83fce2c96efeadb096b6cdaea11e133d4a/lm-pull.py#L262 the current ramalama implementation is based on this but more complex