[Bugfix] fix bug about model type of qwen3_vl_8b_instruct_w8a8 (#7383)

### What this PR does / why we need it?
Adapt to the model type of Qwen3-VL-8B-Instruct-W8A8

- vLLM version: v0.17.0
- vLLM main:
4034c3d32e
---------
Signed-off-by: betta18 <jiangmengyu1@huawei.com>
Co-authored-by: betta18 <jiangmengyu1@huawei.com>

.github/workflows/misc/model_list.json

@@ -222,6 +222,7 @@
       "vllm-ascend/Qwen3-Next-80B-A3B-Instruct-W8A8-Pruning",
       "vllm-ascend/Qwen3-Omni-30B-A3B-Thinking",
       "vllm-ascend/Qwen3-VL-8B-Instruct",
+      "vllm-ascend/Qwen3-VL-8B-Instruct-W8A8",
       "vllm-ascend/TinyLlama-1.1B-Chat-v0.3",
       "vllm-ascend/benchmark",
       "vllm-ascend/ilama-3.2-1B",

.github/workflows/schedule_nightly_test_a2.yaml

@@ -250,6 +250,7 @@ jobs:
           - name: accuracy-group-1
             os: linux-aarch64-a2b3-1
             model_list:
+              - Qwen3-VL-8B-Instruct-W8A8
               - Qwen3-8B
               - Qwen2-Audio-7B-Instruct
               - Qwen3-8B-W8A8

tests/e2e/models/configs/Qwen3-VL-8B-Instruct-W8A8.yaml

@@ -0,0 +1,12 @@
+model_name: "vllm-ascend/Qwen3-VL-8B-Instruct-W8A8"
+hardware: "Atlas A2 Series"
+model: "vllm-vlm"
+tasks:
+- name: "mmmu_val"
+  metrics:
+  - name: "acc,none"
+    value: 0.52
+max_model_len: 8192
+batch_size: 32
+gpu_memory_utilization: 0.8
+quantization: ascend

vllm_ascend/quantization/modelslim_config.py

@@ -57,7 +57,7 @@ QUANT_MODEL_PREFIX_MAPPINGS: dict[str, dict[str, str]] = {
         "language_model.lm_head.": "lm_head.",
         "language_model.model.": "model.language_model.",
     },
-    "qwen3_vl_text": {
+    "qwen3_vl": {
         "visual.": "model.visual.",
         "language_model.lm_head.": "lm_head.",
         "language_model.model.": "model.language_model.",