News for hackers. Stuff that matters.

A comment on Making AMD GPUs competitive for LLM inference. Parent comment

Re:Making AMD GPUs competitive for LLM inference by KeplerBoy on Tuesday December 24, 2024 @08:18AM (#42501722)
At a loss seems a bit overly dramatic. I'd guess Nvidia sells SKUs for three times their marginal cost. Intel is probably operating at cost without any hopes of recouping R&D with the current SKUs, but that's reasonable for an aspiring competitor.
[ Parent | on HN ]
Re:Making AMD GPUs competitive for LLM inference by 7speter on Tuesday December 24, 2024 @01:34PM (#42503846)
It kinda seems they are covering the cost of throwing massive amounts of resources trying to get Arc’s drivers in shape.
[ Parent | on HN ]
Re:Making AMD GPUs competitive for LLM inference by KeplerBoy on Tuesday December 24, 2024 @06:03PM (#42505592)
I really hope they stick with it and become a viable competitor in every market segment a few more years down the line.
[ Parent | on HN ]
Re:Making AMD GPUs competitive for LLM inference by ryao on Wednesday December 25, 2024 @06:18PM (#42511864)
The drivers are shared by their iGPUs, so the cost of improving the drivers is likely shared by those.
[ Parent | on HN ]