Yebs
RRunPod
•Created by Yebs on 3/17/2025 in #⚡|serverless
Can you now run gemma 3 in the vllm container?
In the serverless, its seems im getting an error, any help on this
25 replies
RRunPod
•Created by Yebs on 2/4/2025 in #⚡|serverless
Why serverless endpoints try to repull from container when doing inference?
We using ECR so there a 12 hour token expiration hard to deal with this because somethings no ones there to deal with refreshing the tokens. I find it surprising at the middle of the day endpoints would repull from the container then it will error obviously because the token already expired from the ECR hence the endpoint will not work anymore.
2 replies
RRunPod
•Created by Yebs on 2/2/2025 in #⚡|serverless
Why the serverless downloading instead of "running" when i trigger the runpod id?

4 replies
RRunPod
•Created by Yebs on 2/1/2025 in #⚡|serverless
Max image github repo serverless intergration can take?
.
17 replies