Golden Finance reports that Amazon Web Services has publicly launched its custom AI chip, Trainium3. The company states that the chip's computing speed is four times that of the previous generation AI chips. Compared to systems using equivalent GPUs, Trainium3, produced by AWS's Annapurna Labs custom chip design business, can drop the cost of training and operating AI models by up to 50%. These chips are designed to provide more powerful computing power for software developers, including Dean Lehtsdoff, co-founder and CEO of AI video startup Decart. Lehtsdoff stated that after testing several competitor chips, including Nvidia processors, his company made breakthroughs with Trainium3. The launch of Trainium3 is the latest offensive against Nvidia, which dominates the GPU market, as more and more AI companies are seeking to diversify their suppliers by purchasing chips and other hardware from companies outside of Nvidia.
View Original
This page may contain third-party content, which is provided for information purposes only (not representations/warranties) and should not be considered as an endorsement of its views by Gate, nor as financial or professional advice. See Disclaimer for details.
Amazon launches custom AI chip Trainium3, NVIDIA faces a new round of competition.
Golden Finance reports that Amazon Web Services has publicly launched its custom AI chip, Trainium3. The company states that the chip's computing speed is four times that of the previous generation AI chips. Compared to systems using equivalent GPUs, Trainium3, produced by AWS's Annapurna Labs custom chip design business, can drop the cost of training and operating AI models by up to 50%. These chips are designed to provide more powerful computing power for software developers, including Dean Lehtsdoff, co-founder and CEO of AI video startup Decart. Lehtsdoff stated that after testing several competitor chips, including Nvidia processors, his company made breakthroughs with Trainium3. The launch of Trainium3 is the latest offensive against Nvidia, which dominates the GPU market, as more and more AI companies are seeking to diversify their suppliers by purchasing chips and other hardware from companies outside of Nvidia.