MTIA 300
AssessTools
Meta's in-house accelerator chip for training ranking and recommendation models.
Why it's here
Placed in Assess: 1 article(s) of evidence from 1 source(s), led by research breakthroughs, with 0 in the last 30 days. Confidence 24%. Low accumulated evidence, so it defaults conservatively pending more signal.
Evidence (1)
- 7InfoQ·8/28/2026breakthroughMeta expands custom silicon into networking with MTIA 300
Meta has introduced MTIA 300, its first in-house accelerator designed for training ranking and recommendation models. The move extends Meta’s custom silicon strategy beyond compute into networking-related workloads for its AI infrastructure.