
Sign up to save your podcasts
Or
In a compute world dominated by Nvidia, hyperscalers are looking to build out their own semiconductor infrastructure capable of training and inference workloads at scale.
We chat to AWS product manager Gadi Hutt about his company's approach, based on its 2016 Annapurna Labs acquisition. We talk about Trainium and Inferentia, how the company balances against its GPU fleet, and what it's cooking with Anthropic and Rainier.
4
22 ratings
In a compute world dominated by Nvidia, hyperscalers are looking to build out their own semiconductor infrastructure capable of training and inference workloads at scale.
We chat to AWS product manager Gadi Hutt about his company's approach, based on its 2016 Annapurna Labs acquisition. We talk about Trainium and Inferentia, how the company balances against its GPU fleet, and what it's cooking with Anthropic and Rainier.
1,273 Listeners
1,251 Listeners
2,389 Listeners
503 Listeners
21 Listeners
98 Listeners
11 Listeners
3 Listeners
9,095 Listeners
389 Listeners
7 Listeners
262 Listeners
16 Listeners
461 Listeners
141 Listeners