[Bug] 2卡internvl2-26b推理，卡间通信是pcie会失败，nvlink会成功，这是为啥

### Checklist

- [X] 1. I have searched related issues but cannot get the expected help.
- [X] 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

代码；
backend_config = TurbomindEngineConfig(session_len=8192, tp=2, max_batch_size=2)
pipe = pipeline(model, backend_config=backend_config)
报错；
RuntimeError: [TM][ERROR] CUDA runtime error: out of memory /lmdeploy/src/turbomind/utils/allocator.h:246

### Reproduction

python run.py

### Environment

```Shell
A800 80g
2卡
```

### Error traceback

```Shell
x
```