News for hackers. Stuff that matters.
Re:Nvidia DGX Spark encrypted firmware slows inference speed... by jacquesm on Wednesday November 04, 2026 @10:30AM (#50367002)
That's slower than I would have expected for the RTX 6000, do you have figures for say Qwen 3.8 27B? That model fits completely on the card, that should push it a lot further.
Re:Nvidia DGX Spark encrypted firmware slows inference speed... by barrkel on Thursday November 05, 2026 @08:47AM (#50379014)
I'm pretty certain I can get it to go faster by caching experts and whatnot (with experimental llama.cpp branches), but that would consume a lot more VRAM and it's fast enough as it is for playing around with, and I can leave it always loaded. It's like 50% CPU inference, with a few layers + router + kv cache on the GPU.
Re:Nvidia DGX Spark encrypted firmware slows inference speed... by jacquesm on Thursday November 05, 2026 @05:37PM (#50385500)
Unused VRAM is a crime now, I heard ;)