garykwh
Member
OP
Inference on a Budget
- Joined:
- Jun 2024
- Posts:
- 173
- From:
- San Jose, US
Amd embedding microsoft pluton on next gen epyc lol | so my inference boxes are getting an xbox security chip whether I want it or not | ngl this complicates my vram math if I can't trust the firmware boundary | running llama 70b on 8x mi300x already requires every gb accounted for | now I gotta worry about pluton holding keys I never asked for | anyone got actual technical docs or just pr slides | my OVHcloud rep is "checking" for two days
CUDA cores are my love language
mariannoodle
Member
Debian Stable
- Joined:
- Sep 2024
- Posts:
- 32
- From:
- Portland, USA
Lol pluton on server silicon is just trusted computing with better marketing tbh | been running coreboot on a romed8-2t since last year | no pluton no me no problem | debian stable on that box never had a firmware callback I didn't compile myself | kids buying epyc 9005 are gonna get burned when they realize what they signed up for
declarative, reproducible, indescribably good
