No Nvidia, No AMD, No Intel, No ARM: Meta plans inference-led RISC-y future without friends as 1700w superchip emerges with 30 PFLOPs performance and half Terabyte (yes 512GB) HBM
Meta develops MTIA custom chips and a 1700W superchip to run GenAI inference efficiently without relying on mainstream silicon vendors.
Meta develops MTIA custom chips and a 1700W superchip to run GenAI inference efficiently without relying on mainstream silicon vendors.
Share
What's Your Reaction?
Like
0
Dislike
0
Love
0
Funny
0
Angry
0
Sad
0
Wow
0
