[E2E] Optimize nightly testcase. (#4886)

### What this PR does / why we need it?
Optimize nightly testcase.
Changes:
- tests/e2e/nightly/multi_node/config/models/Qwen3-235B-A3B.yaml: Add
accuracy and performance benchmark
- tests/e2e/models/configs/Qwen3-8B-Base.yaml: Delete
- tests/e2e/models/configs/internlm-7b.yaml: Change to
internlm3-8b-instruct
- tests/e2e/nightly/models/test_deepseek_r1_w8a8_eplb.py: Change to
DeepSeek-R1-0528-W8A8 model

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

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

tests/e2e/models/configs/Qwen3-8B-Base.yaml

@@ -1,14 +0,0 @@
-model_name: "Qwen/Qwen3-8B-Base"
-hardware: "Atlas A2 Series"
-tasks:
-- name: "gsm8k"
-  metrics:
-  - name: "exact_match,strict-match"
-    value: 0.82
-  - name: "exact_match,flexible-extract"
-    value: 0.83
-- name: "ceval-valid"
-  metrics:
-  - name: "acc,none"
-    value: 0.82
-num_fewshot: 5

tests/e2e/models/configs/accuracy.txt

@@ -12,6 +12,6 @@ InternVL3-8B.yaml
 InternVL3_5-8B.yaml
 ERNIE-4.5-21B-A3B-PT.yaml
 gemma-3-4b-it.yaml
-internlm-7b.yaml
+internlm3-8b-instruct.yaml
 Molmo-7B-D-0924.yaml
 llava-1.5-7b-hf.yaml

tests/e2e/models/configs/internlm3-8b-instruct.yaml

@@ -1,4 +1,4 @@
-model_name: "Shanghai_AI_Laboratory/internlm-7b"
+model_name: "Shanghai_AI_Laboratory/internlm3-8b-instruct"
 hardware: "Atlas A2 Series"
 tasks:
 - name: "ceval-valid"