Nvidia DGX Spark encrypted firmware slows inference speed to 35% on Linux

Re:Nvidia DGX Spark encrypted firmware slows inference speed... by f6v on Wednesday November 04, 2026 @07:47AM (#50364826)

But the original post was about a hardware vendor getting in the way. It's pointless to talk about "sovereign AI" when all you do is run GLM on Nvidia.

[ Parent | on HN ]

Re:Nvidia DGX Spark encrypted firmware slows inference speed... by lcampbell on Wednesday November 04, 2026 @10:30AM (#50367000)

To make an apple pie from scratch, you must first invent the universe.

Sovereign AI is less about being able to build it from first principles and more about being able to tinker and modify what already exists. I can’t train a 30B model, but I can modify the weights of one. I can’t fab my own chips, but I can putter with the software that interfaces with them.

Sovereignty is lost when encryption hides your toys and attestation tells you “you may not”.

[ Parent | on HN ]

Re:Nvidia DGX Spark encrypted firmware slows inference speed... by f6v on Wednesday November 04, 2026 @01:59PM (#50370003)

Look, China has sovereign AI because they can train on Huawei GPUs.

Estonian only has sovereign AI as long as they’re allowed to buy from Nvidia. Oh wait, they’re already restricted in what they can get.

[ Parent | on HN ]

Re:Nvidia DGX Spark encrypted firmware slows inference speed... by embedding-shape on Thursday November 05, 2026 @10:15AM (#50380138)

> Look, China has sovereign AI because they can train on Huawei GPUs.

But those servers most likely use CPUs not made in China, if I were to hazard a guess, doesn't that mean that that AI isn't "truly sovereign" in your mind then?

[ Parent | on HN ]

Re:Nvidia DGX Spark encrypted firmware slows inference speed... by lp92 on Friday November 06, 2026 @11:04AM (#50394111)

For now that's the case. But the Chinese government is really pushing for their companies to use local hardware.

[ Parent | on HN ]