Hi everyone and Google Cloud Admins,
I am finalizing my submission for the Med-Gemma Impact Challenge (a multi-modal diagnostic suite for TB and Anemia) and I need a quick lifeline to bypass a strict Google Cloud quota!
To ensure my architecture is cost-efficient and scales to zero, I am deploying the google/medgemma-1.5-4b-it model on Google Cloud Run using the Hugging Face TGI container with a single NVIDIA L4 GPU.
Unfortunately, my project has hit the default 0 quota limit for L4 GPUs.
Could any of the organizers or GCP admins please help expedite this specific quota increase so I can get my MedGemma 4B endpoint live for the judges?
Thank you so much for the help! Sidharth