inference (Page 2)

Modern generative AI model providers require unprecedented computational scale, with pre-training often involving thousands of accelerators running continuously for days, and sometimes months. Foundation Models (FMs) demand distributed training clusters — coordinated groups of accelerated compute instances, using frameworks like PyTorch — to parallelize workloads across hundreds of accelerators (likeContinue Reading

Large language models (LLMs) have revolutionized the way we interact with technology, but their widespread adoption has been blocked by high inference latency, limited throughput, and high costs associated with text generation. These inefficiencies are particularly pronounced during high-demand events like Amazon Prime Day, where systems like Rufus—the Amazon AI-poweredContinue Reading

PixArt-Sigma is a diffusion transformer model that is capable of image generation at 4k resolution. This model shows significant improvements over previous generation PixArt models like Pixart-Alpha and other diffusion models through dataset and architectural improvements. AWS Trainium and AWS Inferentia are purpose-built AI chips to accelerate machine learning (ML)Continue Reading

PixArt-Sigma is a diffusion transformer model that is capable of image generation at 4k resolution. This model shows significant improvements over previous generation PixArt models like Pixart-Alpha and other diffusion models through dataset and architectural improvements. AWS Trainium and AWS Inferentia are purpose-built AI chips to accelerate machine learning (ML)Continue Reading

Headquartered in São Paulo, Brazil, iFood is a national private company and the leader in food-tech in Latin America, processing millions of orders monthly. iFood has stood out for its strategy of incorporating cutting-edge technology into its operations. With the support of AWS, iFood has developed a robust machine learningContinue Reading

Amazon Bedrock cross-Region inference capability that provides organizations with flexibility to access foundation models (FMs) across AWS Regions while maintaining optimal performance and availability. However, some enterprises implement strict Regional access controls through service control policies (SCPs) or AWS Control Tower to adhere to compliance requirements, inadvertently blocking cross-Region inferenceContinue Reading

Deploying models efficiently, reliably, and cost-effectively is a critical challenge for organizations of all sizes. As organizations increasingly deploy foundation models (FMs) and other machine learning (ML) models to production, they face challenges related to resource utilization, cost-efficiency, and maintaining high availability during updates. Amazon SageMaker AI introduced inference componentContinue Reading

This post was co-written with Vishal Singh, Data Engineering Leader at Data & Analytics team of GoDaddy Generative AI solutions have the potential to transform businesses by boosting productivity and improving customer experiences, and using large language models (LLMs) in these solutions has become increasingly popular. However, inference of LLMsContinue Reading

DeepSeek-R1 is a large language model (LLM) developed by DeepSeek AI that uses reinforcement learning to enhance reasoning capabilities through a multi-stage training process from a DeepSeek-V3-Base foundation. A key distinguishing feature is its reinforcement learning step, which was used to refine the model’s responses beyond the standard pre-training andContinue Reading