When using sglang as the inference framework, if a word starting with "\n" appears in the stop parameter, the sglang will Missing '\n' during inference

[nstl-zyb]

LLM model: Qwen2-72B-lora-awq-4bit

python：3.10

sglang：0.2.7

[nstl-zyb]

EG:
prompt = 请换行输出1-10个数字
stop = ['<|endoftext|>', '<|im_end|>', '<|im_start|>']
1
2
3
4
5
6
7
8
9
10

prompt = 请换行输出1-10个数字
stop = ['\n<|endoftext|>', '<|im_end|>', '<|im_start|>']
12345678910

"\n" can be followed by any character, and there will be no line break.

[nstl-zyb]

After Test, its looks wrong in sglang_worker.py where check stop_str. But dont know how to fix.

    async for out, meta_info in state.text_async_iter(
        var_name="response", return_meta_data=True
    ):
        partial_stop = any(is_partial_stop(out, i) for i in stop)

        # prevent yielding partial stop sequence
        if partial_stop:
            continue

        entire_output += out
        prompt_tokens = meta_info["prompt_tokens"]
        completion_tokens = meta_info["completion_tokens"]

        ret = {
            "text": entire_output,
            "usage": {
                "prompt_tokens": prompt_tokens,
                "completion_tokens": completion_tokens,
                "total_tokens": prompt_tokens + completion_tokens,
            },
            "error_code": 0,
        }
        yield ret

[nstl-zyb]

This is the bug code when deal stop_str.