return the last token's logprobs, logits and last_hidden_states if include_stop_str_in_output is requested

[lvhan028]

No description provided.

[lvhan028]

lmdeploy serve api_server Qwen/Qwen3-8B --backend pytorch --logprobs-mode raw_logprobs

from openai import OpenAI
client = OpenAI(api_key='11', base_url='http://0.0.0.0:23333/v1/')
model_name = client.models.list().data[0].id

response = client.chat.completions.create(
    model=model_name,
    messages=[{
        'role': 'user',
        'content': "Hello!",
    }],
    temperature=0.8,
    top_p=0.8,
    logprobs=True,
    top_logprobs=1,
    stream=False,
    extra_body={
        "include_stop_str_in_output": True,
        "return_token_ids": True,
    })
logprobs = []
for item in response.choices[0].logprobs.content:
    logprobs.append(item.logprob)
print(len(logprobs), logprobs)
print(len(response.choices[0].message.gen_tokens), response.choices[0].message.gen_tokens)
print(response)

The logprobs of <|im_end|> is supposed to be output