Directly answering your question requires making some assumptions about what you mean and also what "class" of models you are asking about. Unfortunately I don't think it's just a yes or no, since I can answer in both directions depending on the interpretation.If you mean "during inference", then the answer is mostly no in my opinion, but it depends on what you are calling a "LLM" and "processing power", haha. If you mean everything behind an endpoint is an LLM, eg. that includes a RAG system, s...