Che Jami@cjami

Gulliver's Router reduces cloud usage by handling suitable prompts locally. It sends work to the cloud when the expected improvement in answer quality justifies the extra cost. Under the hood, it uses small classifiers trained on judged local and cloud responses. They flag prompts where the local model is likely to fall short, identify the task category, and let the runtime use specialist paths for jobs like named entity extraction and arithmetic. The result is a router that stays practical for resource-constrained environments. It also features a bailout if time draws near to the 10 minute mark - evacuating all local tasks to the cloud.

To participate in the hackathon, simply click Sign up with AMD. If you are not already a member of the AMD AI Developer Program (ADP), you will need to create an account. ADP members can access AI tutorials, experts, and community support. In addition, new members can claim a free month of DeepLearning.ai pro, $100 in AMD GPU cloud credits, and $50 in Fireworks AI API credits. All hackathon participants will receive on hackathon launch additional compute and API credits for their projects. Ready to build what's next on AMD? Sign up with AMD below to secure your spot.