Powering real-time vision-language model inference for conversational visual discovery and search
Stated outcome: 44x faster end-to-end latency
Pinterest built its platform around two foundational choices: NVIDIA Blackwell B200 GPUs as the compute layer, and NVIDIA Dynamo as the serving orchestration framework.
From Pinterest Accelerates Visual AI With NVIDIA Blackwell | NVIDIA, nvidia.com.Checked Oct 18, 2026 Pinterest stack · Nvidia customers
Unverified: found by the daily run and not yet checked by hand.