[Misc] Add new models for moe lora e2e tests. (vllm-project#11087)

### What this PR does / why we need it?
Add new models for moe lora e2e tests.
List:
- allenai/OLMoE-1B-7B-0125-Instruct
- vllm-ascend/qwen3-moe-text2sql-spider
- vllm-ascend/olmoe-instruct-text2sql-spider

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

### How was this patch tested?
No.

- vLLM version: v0.23.0
- vLLM main:
vllm-project/vllm@1f486d9

Signed-off-by: paulyu12 <507435917@qq.com>

Author: paulyu12

.github/workflows/misc/model_dataset_list.json

@@ -125,6 +125,7 @@
       "Tencent-Hunyuan/Hy3-preview",
       "Tengyunw/qwen3_8b_eagle3",
       "Tongyi-MAI/Z-Image-Turbo",
+      "allenai/OLMoE-1B-7B-0125-Instruct",
       "baichuan-inc/Baichuan2-7B-Chat",
       "billy800/Qwen3-30B-A3B-Instruct-2507-AWQ",
       "deepseek-ai/DeepSeek-OCR",
@@ -260,6 +261,8 @@
       "vllm-ascend/qwen2vl-flickr-lora-tower-connector",
       "vllm-ascend/qwen2vl-flickr-lora-tower",
       "vllm-ascend/qwen35-4b-text-only-sql-lora",
+      "vllm-ascend/qwen3-moe-text2sql-spider",
+      "vllm-ascend/olmoe-instruct-text2sql-spider",
       "wemaster/deepseek_mtp_main_random_bf16",
       "wemaster/deepseek_mtp_main_random_w8a8_part",
       "xlangai/OpenCUA-7B",