[CI] Upgrade ci npu to 64g per chip

.github/workflows/accuracy_test.yaml

@@ -85,8 +85,8 @@ jobs:
       }}
     runs-on: >-
       ${{
-          (matrix.model_name == 'Qwen/Qwen3-30B-A3B' && 'linux-arm64-npu-4') ||
-          'linux-arm64-npu-2'
+          (matrix.model_name == 'Qwen/Qwen3-30B-A3B' && 'linux-arrch64-a2-2') ||
+          'linux-arrch64-a2-1'
       }}
     strategy:
       matrix:

.github/workflows/vllm_ascend_doctest.yaml

@@ -48,7 +48,7 @@
       matrix:
         vllm_verison: [v0.9.1-dev, v0.9.1-dev-openeuler, main, main-openeuler]
     name: vLLM Ascend test
-    runs-on: linux-arm64-npu-1
+    runs-on: linux-arrch64-a2-1
     container:
       image: m.daocloud.io/quay.io/ascend/vllm-ascend:${{ matrix.vllm_verison }}
     steps:

.github/workflows/vllm_ascend_test.yaml

@@ -200,7 +200,7 @@
     strategy:
       max-parallel: 2
       matrix:
-        os: [linux-arm64-npu-1]
+        os: [linux-arrch64-a2-1]
         vllm_version: [main, v0.9.2]
     name: singlecard e2e test
     runs-on: ${{ matrix.os }}
@@ -299,9 +299,9 @@
     needs: [e2e]
     if: ${{ needs.e2e.result == 'success' }}
     strategy:
-      max-parallel: 1
+      max-parallel: 2
       matrix:
-        os: [linux-arm64-npu-4]
+        os: [linux-arrch64-a2-2]
         vllm_version: [main, v0.9.2]
     name: multicard e2e test
     runs-on: ${{ matrix.os }}

.github/workflows/vllm_ascend_test_long_term.yaml

@@ -42,7 +42,7 @@
     strategy:
       max-parallel: 2
       matrix:
-        os: [linux-arm64-npu-1, linux-arm64-npu-4]
+        os: [linux-arrch64-a2-1, linux-arrch64-a2-2]
         vllm_version: [main, v0.9.2]
     name: vLLM Ascend long term test
     runs-on: ${{ matrix.os }}

benchmarks/scripts/run_accuracy.py

@@ -50,17 +50,17 @@
 # Command templates for running evaluations
 MODEL_RUN_INFO = {
     "Qwen/Qwen3-30B-A3B":
-    ("export MODEL_ARGS='pretrained={model},max_model_len=4096,dtype=auto,tensor_parallel_size=4,gpu_memory_utilization=0.6,enable_expert_parallel=True'\n"
+    ("export MODEL_ARGS='pretrained={model},max_model_len=4096,dtype=auto,tensor_parallel_size=2,gpu_memory_utilization=0.6,enable_expert_parallel=True'\n"
      "lm_eval --model vllm --model_args $MODEL_ARGS --tasks {datasets} \ \n"
      "--apply_chat_template --fewshot_as_multiturn --num_fewshot 5 --batch_size 1"
      ),
     "Qwen/Qwen3-8B-Base":
-    ("export MODEL_ARGS='pretrained={model},max_model_len=4096,dtype=auto,tensor_parallel_size=2,gpu_memory_utilization=0.6'\n"
+    ("export MODEL_ARGS='pretrained={model},max_model_len=4096,dtype=auto,tensor_parallel_size=1,gpu_memory_utilization=0.6'\n"
      "lm_eval --model vllm --model_args $MODEL_ARGS --tasks {datasets} \ \n"
      "--apply_chat_template --fewshot_as_multiturn --num_fewshot 5 --batch_size 1"
      ),
     "Qwen/Qwen2.5-VL-7B-Instruct":
-    ("export MODEL_ARGS='pretrained={model},max_model_len=8192,dtype=auto,tensor_parallel_size=2,max_images=2'\n"
+    ("export MODEL_ARGS='pretrained={model},max_model_len=8192,dtype=auto,tensor_parallel_size=1,max_images=2'\n"
      "lm_eval --model vllm-vlm --model_args $MODEL_ARGS --tasks {datasets} \ \n"
      "--apply_chat_template --fewshot_as_multiturn  --batch_size 1"),
 }
@@ -102,11 +102,11 @@
 # Model arguments for evaluation
 MODEL_ARGS = {
     "Qwen/Qwen3-8B-Base":
-    "pretrained=Qwen/Qwen3-8B-Base,max_model_len=4096,dtype=auto,tensor_parallel_size=2,gpu_memory_utilization=0.6",
+    "pretrained=Qwen/Qwen3-8B-Base,max_model_len=4096,dtype=auto,tensor_parallel_size=1,gpu_memory_utilization=0.6",
     "Qwen/Qwen2.5-VL-7B-Instruct":
-    "pretrained=Qwen/Qwen2.5-VL-7B-Instruct,max_model_len=8192,dtype=auto,tensor_parallel_size=2,max_images=2",
+    "pretrained=Qwen/Qwen2.5-VL-7B-Instruct,max_model_len=8192,dtype=auto,tensor_parallel_size=1,max_images=2",
     "Qwen/Qwen3-30B-A3B":
-    "pretrained=Qwen/Qwen3-30B-A3B,max_model_len=4096,dtype=auto,tensor_parallel_size=4,gpu_memory_utilization=0.6,enable_expert_parallel=True"
+    "pretrained=Qwen/Qwen3-30B-A3B,max_model_len=4096,dtype=auto,tensor_parallel_size=2,gpu_memory_utilization=0.6,enable_expert_parallel=True"
 }
 
 # Whether to apply chat template formatting