Comments on: Meta AI Acceleration in the Next-Gen Meta MTIA for Recommendation Inference https://www.servethehome.com/meta-ai-acceleration-in-the-next-gen-meta-mtia-for-recommendation-inference-risc-v/ Server and Workstation Reviews Thu, 29 Aug 2024 20:41:20 +0000 hourly 1 https://wordpress.org/?v=6.7.1 By: Oleg https://www.servethehome.com/meta-ai-acceleration-in-the-next-gen-meta-mtia-for-recommendation-inference-risc-v/#comment-584812 Thu, 29 Aug 2024 20:41:20 +0000 https://www.servethehome.com/?p=80348#comment-584812 Your estimated power consumption for the card seems inaccurate. Given that each card has 36 modules (2 MTIA per module) with a TDP of 220W, the total power consumption per card is approximately 8kW. This suggests that the entire rack would draw significantly less than 20kW, which is a typical rack power limit. Which is a breeze compared to Blackwell-based racks.

]]>
By: Justin https://www.servethehome.com/meta-ai-acceleration-in-the-next-gen-meta-mtia-for-recommendation-inference-risc-v/#comment-584780 Thu, 29 Aug 2024 12:23:19 +0000 https://www.servethehome.com/?p=80348#comment-584780 There is a typo in sram size.

]]>