fix return_token_log_probs on vLLM > 0.3.3 endpoints

[saiatmakuri]

Pull Request Summary

since vLLM > 0.3.3, logprobs are returned as as type Logprob instead as direct float's. it's an API-breaking change (see vllm-project/vllm#3065 (comment))

change vllm_server to return output in the same previous format

Test Plan and Usage Guide

create new llama-2-7b with vLLM==0.4.0.post1

Completion.create(
    model="llama-2-7b",
    prompt="Hello ",
    max_new_tokens=10,
    temperature=0.0,
    return_token_log_probs=True,
)

[yunfeng-scale]

thanks for the fix! i think we need to do some backfills also?

[saiatmakuri]

thanks for the fix! i think we need to do some backfills also?

will update endpoints to latest image post merge