Hi there, I'm trying to run LLM inference example ...
# ask-for-help
m
Hi there, I'm trying to run LLM inference example (https://docs.bentoml.com/en/latest/examples/vllm.html) but after launching bentoml deploy command I get the following error: [bentoml-cli]
deploy
failed: request failed with status code 400: {"error":"create deployment: deploy deployment revision: failed to deploy kube bento function: failed to transform to kube bento function: failed to get resources from resource instance: you are not allowed to use this resource instance: starter-gcp-g2-standard-8-gpu-l4-1"}. Any idea?
j
Hello! What is the organization name that you were trying to deploy onto?
m
@Jian Shen Yap marcovic