#

two-tier-inference

Here are 2 public repositories matching this topic...

aws-samples / sample-nvidia-nemotron-cascade-workshop

Sample code for two-tier LLM inference (cascading) on Amazon Bedrock, using a single Bedrock Converse API surface. NVIDIA Nemotron Nano handles routine support-ticket classification on every request; Anthropic Claude Sonnet handles cases the routing logic flags as harder. Includes a bake-off harness, sample data, and tests. Next.js + TypeScript.

typescript workshop nextjs mit-0 anthropic-claude amazon-bedrock aws-samples nvidia-nemotron model-routing llm-cost-optimization llm-cascade bedrock-converse-api two-tier-inference

Updated Sep 7, 2026
TypeScript

Toastee0 / recamera-lite

Two-tier salience-gated vision for the Seeed reCamera: on-device NPU gates, a local GPU YOLO confirms.

computer-vision yolo object-detection npu edge-ai sg2002 recamera two-tier-inference

Updated Jul 15, 2026
C++

Add this topic to your repo

To associate your repository with the two-tier-inference topic, visit your repo's landing page and select "manage topics."