Thorsten Glaser <t...@debian.org> writes: >>How about removing that paragraph and replace 'non-free' with >>'non-free(-firmware)' in the rest of your proposal? > > Not sure this is the right fix. What I wanted to say is: models are, > while data, run on the main system (CPU) or as main workload (this part > is important) on adjacent chips (GPU, specific ASIC/FPGA); models are > not a firmware in the sense of enabling the use of such hardware and > therefore not for non-free-firmware. So, in that direction: models we’d > have packaged as models, used by ordinary packages on the system, driven > by the user (or an automatism on their behalf).
I don't understand your point here, can you explain it differently? I don't think it is possible to separate firmware into things that are just for enabling of hardware compared to what is running on the main CPU. Consider a non-free firmware blob for a future SoC CPU that includes camera functionality, it seems possible that would make use of some LLM model to have better face recognition for example. Without disassembly (which may be illegal) we can't really know if this is part of the blob or not. > The other direction, if there’s non-free-firmware that *also* includes > models: yes, we cannot control that, and I’d be fine with that as long > as these models are ⓐ a part of the firmware in question (and not pak‐ > kaged separately) as well as ⓑ not available/used by packages in main > (or contrib) for purposes beyond how the firmware itself, running on its > separate chip, uses them. I'm not sure I understand fully here, but I wonder if what you are trying to express really works. Non-free firmware is loaded into the main CPU on many Intel and AMD systems, and I think it won't be long until CPUs won't even start (and thus eventually used by packages in main) if it doesn't have the non-free blob provided to it, and that it can include a small LLM model. Another use-case for small LLM models could be fingerprint readers. /Simon
signature.asc
Description: PGP signature
