vllm + chatglm3, it can't generate content as expected

Nobody has claimed this yet.

When using vllm + ChatGLM3 and accessing the openai API, it cannot generate content. The reason is that:

1. In `conversation.py`, the ChatGLM3 template has a `stop_token_ids` with ID `2`:
```python
register_conv_template(
    Conversation(
        name="chatglm3",
        system_template="<|system|>\n {system_message}",
        roles=("<|user|>", "<|assistant|>"),
        sep_style=SeparatorStyle.CHATGLM3,
        stop_token_ids=[
            64795,
            64797,
            2,
        ],  # "<|user|>", "<|observation|>", ""
    )
)
```

2. The `generate_stream` method in `vllm_worker.py` converts `stop_token_ids` into stop words. The token with ID `2` becomes an empty string after decoding:
```python
        for tid in stop_token_ids:
            if tid is not None:
                stop.add(self.tokenizer.decode(tid))
```
Then the `SamplingParams` are:
```python
SamplingParams(n=1, best_of=1, presence_penalty=0.0, frequency_penalty=0.0, repetition_penalty=1.0, temperature=0.5, top_p=1.0, top_k=-1, min_p=0.0, use_beam_search=False, length_penalty=1.0, early_stopping=False, stop=['', '<|observation|>', '<|user|>'], stop_token_ids=[64795, 64797, 2, 2], ignore_eos=False, max_tokens=32750, logprobs=None, prompt_logprobs=None, skip_special_tokens=True, spaces_between_special_tokens=True)
```
The param `stop` contains '', so it cannot generate normally.

Start with conversation.py to inspect the ChatGLM3 stop_token_ids and vllm_worker.py to trace how those IDs become stop words. Reproduce the issue through the OpenAI API and verify that SamplingParams no longer contains an empty stop string while generation completes normally.

Written by the indexing model from the issue text.