[E2E] Refactor the e2e testcases. (#4789)

### What this PR does / why we need it?
Refactor the e2e testcases.
- tests/e2e/multicard/test_weight_loader.py: Remove the unused code.
- tests/e2e/singlecard/multi-modal/test_internvl.py: Move to accuracy
test.
- tests/e2e/singlecard/test_aclgraph.py: Rename the file.
- tests/e2e/singlecard/test_embedding_aclgraph.py : Combine with
tests/e2e/singlecard/test_bge_model.py
- tests/e2e/singlecard/test_completion_with_prompt_embeds.py: Delete
eager mode and modify model to Qwen3-0.6B
- tests/e2e/singlecard/test_quantization.py: Modify model to
Qwen3-0.6B-W8A8
- tests/e2e/singlecard/test_vlm.py: Modify model to Qwen3-VL-8B

- vLLM version: v0.12.0
- vLLM main:
ad32e3e19c

---------

Signed-off-by: menogrey <1299267905@qq.com>

tests/e2e/models/configs/InternVL2-8B.yaml

@@ -0,0 +1,11 @@
+model_name: "OpenGVLab/InternVL2-8B"
+runner: "linux-aarch64-a2-1"
+hardware: "Atlas A2 Series"
+model: "vllm-vlm"
+tasks:
+  - name: "mmmu_val"
+    metrics:
+    - name: "acc,none"
+      value: 0.58
+max_model_len: 32768
+trust_remote_code: True

tests/e2e/models/configs/InternVL2_5-8B.yaml

@@ -0,0 +1,11 @@
+model_name: "OpenGVLab/InternVL2_5-8B"
+runner: "linux-aarch64-a2-1"
+hardware: "Atlas A2 Series"
+model: "vllm-vlm"
+tasks:
+  - name: "mmmu_val"
+    metrics:
+    - name: "acc,none"
+      value: 0.58
+max_model_len: 32768
+trust_remote_code: True

tests/e2e/models/configs/InternVL3-8B.yaml

@@ -0,0 +1,11 @@
+model_name: "OpenGVLab/InternVL3-8B"
+runner: "linux-aarch64-a2-1"
+hardware: "Atlas A2 Series"
+model: "vllm-vlm"
+tasks:
+  - name: "mmmu_val"
+    metrics:
+    - name: "acc,none"
+      value: 0.58
+max_model_len: 32768
+trust_remote_code: True

tests/e2e/models/configs/accuracy.txt

@@ -6,6 +6,9 @@ Qwen3-VL-30B-A3B-Instruct.yaml
 Qwen3-VL-8B-Instruct.yaml
 Qwen2.5-Omni-7B.yaml
 Meta-Llama-3.1-8B-Instruct.yaml
+InternVL2-8B.yaml
+InternVL2_5-8B.yaml
+InternVL3-8B.yaml
 InternVL3_5-8B.yaml
 ERNIE-4.5-21B-A3B-PT.yaml
 gemma-3-4b-it.yaml