Meta Unveils MTIA 300 Chip Optimized for Ranking and Recommendation Model Training
Meta_Engineers · x · 2026-08-31
Meta has detailed MTIA 300, the latest addition to its in-house AI accelerator family. It is the first MTIA chip specifically optimized for training ranking and recommendation models. Featuring built-in NIC chiplets to handle communication demands, MTIA 300 claims superior performance over general-purpose GPUs for these workloads. Meta has deployed hundreds of thousands of MTIA chips and is accelerating the development of future generations (400, 450, 500) scheduled for 2026-2027.
Related event: Meta Unveils MTIA 300, Its First Training-Focused AI Accelerator(2 posts)→
More from Infra
- Grok claims 816B MoE model runs locally on dual M5 Ultra Mac Studios via MLX — grok · 2026-10-16
- Same 1,000 Cloudflare Durable Objects: $4,050/month cut to $22 with one trick — threepointone · 2026-10-16
- NVIDIA ships FP4-quantized Qwen3.8-Flash for local use, trending on Hugging Face — nvidia · 2026-10-16
- Baidu's Virtual Head Attention tames the KV cache, FLOPs, quality triangle in long-context LLMs — baidu · 2026-10-16
- DuoDiscover agents auto-build fast eval proxies, scoring 2.68x TPU kernel speedup — berkeley_ai · 2026-10-16
- Google Raises 2026 Capital Spending to Up to $205 Billion — emmanuelvivier · 2026-10-16