Page: https://bentoml.com/llm/llm-inference-basics/serverless-vs-self-hosted-llm-inference
There's a third and important option for infrastructure, models hosted by AWS, GCP and Azure. For example: Amazon Bedrock, Vertex AI and Azure AI Foundry. This option is good for companies that plan to fine-tune models but don't want the hassle of self-hosting.
Page: https://bentoml.com/llm/llm-inference-basics/serverless-vs-self-hosted-llm-inference
There's a third and important option for infrastructure, models hosted by AWS, GCP and Azure. For example: Amazon Bedrock, Vertex AI and Azure AI Foundry. This option is good for companies that plan to fine-tune models but don't want the hassle of self-hosting.