[CI] Cache sampled token ids in model runner to fix CI error (#1573)

### What this PR does / why we need it?
vllm change
7f280d69c9
break vllm-ascend.

This PR Fix the broken CI

### Does this PR introduce _any_ user-facing change?
No

### How was this patch tested?
passed

Closes: https://github.com/vllm-project/vllm-ascend/issues/1572

Signed-off-by: wangxiyuan <wangxiyuan1007@gmail.com>

tests/e2e/singlecard/test_ilama_lora.py

@@ -1,5 +1,4 @@
 # SPDX-License-Identifier: Apache-2.0
-
 import vllm
 from vllm.lora.request import LoRARequest