Meta 披露 MTIA 以六个月节奏流片，靠 chiplet 复用提速
Chiplets: Meta-Scale Chiplet Velocity Accelerating AI SoC Development to Match the Rapid Evolution of AI Model
Meta 杰出工程师 Olivia Wu 在演讲中介绍，Meta Infra Silicon 团队以六个月为周期完成 SoC 流片，已连续交付四代 MTIA，覆盖排序推荐训练到大规模生成式 AI 推理。她称 chiplet 架构把系统拆成模块化裸片，使增强 HBM 带宽、面向 MoE 的 MX4 精度和 die-to-die 互连可逐代引入，并复用已验证 IP 重新封装成差异化产品。
这条信号在站内保留事实摘要与战略研判。完整内容和上下文请以原文为准；融资、并购与技术效果以原始披露为准。
This event session is presented by Olivia Wu, Distinguished Engineer at Meta AI model architectures are evolving faster than traditional chip development cycles, and at Meta’s scale—serving billions of users across ranking & recommendation and generative AI workloads—this mismatch is untenable. Meta’s Infra Silicon team has responded with a six-month SoC tape-out cadence, delivering four […] The post Chiplets: Meta-Scale Chiplet Velocity Accelerating AI SoC Development to Match the Rapid Evolution of AI Model appeared first on EE Times .
来源只提供摘要，完整内容请打开原文。
来源：EE Times · eetimes.com
所属事件：Meta披露MTIA芯片六个月流片节奏