Sprinklr improves performance by 20% and reduces cost by 25% for machine learning inference on AWS Graviton3

This article discusses how Sprinklr optimized their machine learning inference performance and reduced costs by migrating to AWS Graviton3 instances.

Specifically, the article covers:

• Sprinklr's AI scale and challenges with diverse AI workloads
• Cost-effective ML inference using AWS Graviton3
• Sprinklr's two-step approach to migration: benchmarking and integration
• Results: 20% throughput improvement, 30% latency reduction, 25-30% cost savings
• Conclusion highlighting the benefits of using Graviton3 instances