[Bug] tp>1时，进行多视频batch推理没有结果输出

[qingchunlizhi]

Checklist

• 1. I have searched related issues but cannot get the expected help.
• 2. The bug has not been fixed in the latest version.
• 3. Please note that if the bug-related issue you submitted lacks corresponding environment info and a minimal reproducible demo, it will be challenging for us to reproduce and resolve the issue, reducing the likelihood of receiving feedback.

Describe the bug

目标是使用lmdeploy加速多视频batch推理，输入排版大致如下：
[[],[]...]
但是使用tp=8，模型输入结果为空。请问是不支持多视频batch推理吗？

Reproduction

pipe = pipeline('/xx/InternVL2_5-38B-MPO-AWQ', backend_config=TurbomindEngineConfig(session_len=10000, tp=8))

Environment

InternVL2_5-38B-MPO-AWQ

Error traceback