Grab has modernized its machine learning model serving platform, Catwalk, by adopting NVIDIA Triton Inference Server to enhance performance and reduce costs. The transition involved creating a "Triton manager" for seamless integration and backward compatibility, resulting in significant improvements in latency and infrastructure spending for deployed models.
+ model-serving
nvidia-triton ✓
machine-learning ✓
performance-optimization ✓
infrastructure ✓