Eric Curtin

icon indicating a website link https://www.linkedin.com/in/curtine icon indicating an email [email protected]

icon company Red Hat icon location Ireland icon location https://gitlab.com/ecurtin https://gitlab.freedesktop.org/ecurtin

Results 479 comments of Eric Curtin

Enhanced docker support for "bootc switch"

@cgwalters I am trying to use skopeo, but if that doesn't work out, maybe bootc docker can interact directly. WDYT?

Enhanced docker support for "bootc switch"

We may want to bypass skopeo docker-daemon anyway, performance seems shocking, takes a long time and eats up CPU hard...

Enhanced docker support for "bootc switch"

Closing

RamaLama won't recognize RX5700XT

Maybe you need this fix? https://github.com/containers/ramalama/pull/802

RamaLama won't recognize RX5700XT

It's `--ngl 999` rather than `--ngl=999`

RamaLama won't recognize RX5700XT

You need to put it after the run command I think

RamaLama won't recognize RX5700XT

Can you try updating the version of ramalama, this ngl thing was added recently enough

RamaLama won't recognize RX5700XT

Could you paste the full "--debug" output? Also what are you using to check if the GPU is being utilised? nvtop? 5 seconds reasonable to initialized a GPU. Might be...

RamaLama won't recognize RX5700XT

@Split7fire seems like llama-run/llama-bench is crashing then, you'll need to debug this in the llama.cpp layer

AI models in microVMs

First attempt, GPU passthrough isn't working (I tried with AMD GPU) and there's some weird issue where ">" displays as "e", could be because of the emoji or TERM or...