Meta plans to deploy ‘Artemis’ to reduce dependency on Nvidia
Meta Platforms, the parent company of Facebook, is planning to deploy a second-generation custom chip into its data centers this year, according to an internal document obtained by Reuters. This move is part of Meta’s ongoing efforts to enhance its artificial intelligence (AI) capabilities and reduce reliance on Nvidia chips.
Meta aims to reduce its reliance on Nvidia for AI-focused chips
The new chip, known internally as “Artemis,” follows the announcement of a custom silicon line by Meta last year. The goal is to not only cut costs associated with running AI workloads but also reduce reliance on Nvidia for AI-focused chips as Meta intensifies its push into generative AI products across Facebook, Instagram, WhatsApp, and hardware devices like Ray-Ban smart glasses.
The deployment of Meta’s own chip could potentially lead to significant savings, reducing annual energy costs and billions in chip purchasing expenses. Dylan Patel, founder of the silicon research group SemiAnalysis, suggests that at Meta’s scale, the successful deployment of its custom chip could result in substantial financial benefits. The move signifies Meta’s attempt to establish greater control over its AI infrastructure.
Meta expects performance and efficiency improvement on its specific workloads with “Artemis”
Meta’s plan to complement commercially available AI-focused GPUs with its internally developed Artemis chips aims to optimize performance and efficiency on Meta-specific workloads. The company’s CEO, Mark Zuckerberg, recently outlined plans to acquire around 350,000 Nvidia H100 processors by the end of the year, highlighting the substantial computing capacity Meta aims to accumulate.
The new chip, Artemis, is designed for inference processing, where models use algorithms to generate responses to user prompts. Despite a setback in 2022 when executives decided to abandon the first iteration of the chip, Meta’s renewed focus on in-house AI silicon marks a positive development. The company had initially chosen to purchase Nvidia’s GPUs, which currently dominate the AI training process. While currently focused on inference, the Artemis chip indicates Meta’s exploration of more ambitious chips capable of handling training and inference, as reported last year.
Meta Platforms, the parent company of Facebook, is planning to deploy a second-generation custom chip into its data centers this year, according to an internal document obtained by Reuters. This move is part of Meta’s ongoing efforts to enhance its artificial intelligence (AI) capabilities and reduce reliance on Nvidia chips.
Meta aims to reduce its reliance on Nvidia for AI-focused chips
The new chip, known internally as “Artemis,” follows the announcement of a custom silicon line by Meta last year. The goal is to not only cut costs associated with running AI workloads but also reduce reliance on Nvidia for AI-focused chips as Meta intensifies its push into generative AI products across Facebook, Instagram, WhatsApp, and hardware devices like Ray-Ban smart glasses.
The deployment of Meta’s own chip could potentially lead to significant savings, reducing annual energy costs and billions in chip purchasing expenses. Dylan Patel, founder of the silicon research group SemiAnalysis, suggests that at Meta’s scale, the successful deployment of its custom chip could result in substantial financial benefits. The move signifies Meta’s attempt to establish greater control over its AI infrastructure.
Meta expects performance and efficiency improvement on its specific workloads with “Artemis”
Meta’s plan to complement commercially available AI-focused GPUs with its internally developed Artemis chips aims to optimize performance and efficiency on Meta-specific workloads. The company’s CEO, Mark Zuckerberg, recently outlined plans to acquire around 350,000 Nvidia H100 processors by the end of the year, highlighting the substantial computing capacity Meta aims to accumulate.
The new chip, Artemis, is designed for inference processing, where models use algorithms to generate responses to user prompts. Despite a setback in 2022 when executives decided to abandon the first iteration of the chip, Meta’s renewed focus on in-house AI silicon marks a positive development. The company had initially chosen to purchase Nvidia’s GPUs, which currently dominate the AI training process. While currently focused on inference, the Artemis chip indicates Meta’s exploration of more ambitious chips capable of handling training and inference, as reported last year.
Denial of responsibility! Techno Blender is an automatic aggregator of the all world’s media. In each content, the hyperlink to the primary source is specified. All trademarks belong to their rightful owners, all materials to their authors. If you are the owner of the content and do not want us to publish your materials, please contact us by email – [email protected]. The content will be deleted within 24 hours.