AWS plans to deploy Cerebras' Wafer-Scale Engine chip for AI inference functions; AWS will still offer slower, cheaper computing using its Trainium processors
Amazon Web Services says the partnership will allow it to offer lightning-fast inference computing
Wall Street Journal
Related Coverage
- AWS partners with big chip co. Cerebras for AI “inference disaggregation” DatacenterDynamics · Charlotte Trueman
- Amazon Will Use Cerebras' Giant Chips to Help Run AI Models Bloomberg · Ian King
- Meta's MTIA Roadmap: Four Chip Generations in Two Years Put GenAI Inference First StorageReview.com · Harold Fritts
- Amazon (AMZN) Stock: AWS Partners With Cerebras to Challenge Nvidia's AI Chip Dominance Blockonomi · Trader Edge
- AWS Aims to Boost AI Business With Cerebras Chip Deal The Information · Kevin McLaughlin
- Nvidia may soon unveil a brand-new AI chip. A closer look at the $20 billion bet to make it happen CNBC · Kevin Stankiewicz
- Amazon's AWS Partners With Cerebras Systems To Deliver Faster AI Inference For LLMs Benzinga
- Twenty years after pioneering the cloud, Amazon Web Services chases the next big prize: AI SiliconANGLE · Robert Hof
- Preparing Enterprise Data Centers for AI Adoption Data Center Knowledge · Kirk Killian
- Hot Picks: Amazon-OpenAI deal seen boosting AI compute growth BNN Bloomberg
- AWS and Cerebras Collaboration Aims to Set a New Standard for AI Inference in the Cloud AIwire · Jaime Hampton
- Breaking News: Amazon is deploying Cerebras Wafer Scale Engines in AWS datacenters ! — This means ultra fast inference will be available through AWS Bedrock … Kim Ziesemer
- AWS will bring Cerebras' wafer-size WSE-3 chip to its cloud platform SiliconANGLE · Maria Deutscher
- AWS and Cerebras collaboration aims to set a new standard for AI inference speed and performance in the cloud About Amazon
- Amazon Imposes AI Coding Oversight Benzinga · Funso Lawal
Discussion
-
@sethwinterroth
Seth Winterroth
on x
Cerebras just landed AWS. That's @OpenAI and @awscloud in the span of 3 months. The AI inference stack is restructuring in real time and @cerebras is winning. https://www.wsj.com/...
-
@bgurley
Bill Gurley
on x
That's big. Really big. Whole wafer big.
-
@tbu12345678
@tbu12345678
on x
legit hysterical that Cerebras got a presser from AWS before $AMD
-
@awscloud
@awscloud
on x
We're teaming up with @cerebras to build the fastest possible inference. Coming soon to Amazon Bedrock, we're delivering inference performance an order of magnitude faster than what's available today by connecting AWS Trainium3 for compute-intensive prefill with Cerebras CS-3 [vi…
-
@ericvishria
Eric Vishria
on x
Breaking up prefill (processing the prompt) and decode (generating the response) has been theorized for a while as they have different compute requirements. Now we have the silicon to do it - AWS Trainium for prefill, and Cerebras for decode. Super fast AND cost effective.
-
@andrewdfeldman
Andrew Feldman
on x
Today Cerebras announced that @awscloud will be deploying Cerebras CS-3s in their data centers. Together, Cerebras and AWS will be delivering the fastest inference solution in the world. It has been an extraordinary 30 days for Cerebras. In February, we announced that we would [i…
-
@awsnewsroom
@awsnewsroom
on x
AWS and @cerebras are bringing dramatically faster AI inference to customers through Amazon Bedrock. The solution splits inference into two stages: AWS Trainium3 for prompt processing and Cerebras CS-3 for output generation. AWS will be the first and exclusive cloud provider to […