[BugFix] Fix a bug of running chunked-prefill with torchair. (#1378) (#1844)

This PR fixes the bug `local variable 'decode_hs_or_q_c' referenced
before assignment` when running chunked-prefill with torchair. We should
calculate `decode_hs_or_q_c` whether or not torchair graphics mode is
enabled.

backport of #1378
fix https://github.com/vllm-project/vllm-ascend/issues/1369


- vLLM version: v0.10.0
- vLLM main:
0e36abf993

---------

Signed-off-by: whx-sjtu <2952154980@qq.com>
Signed-off-by: MengqingCao <cmq0113@163.com>
Co-authored-by: whx-sjtu <2952154980@qq.com>

tests/e2e/multicard/test_torchair_graph_mode.py

@@ -31,6 +31,7 @@ def _deepseek_torchair_test_fixture(
     additional_config: Dict,
     *,
     tensor_parallel_size=2,
+    use_v1_schduler=False,
 ):
     example_prompts = [
         "Hello, my name is",
@@ -38,14 +39,14 @@ def _deepseek_torchair_test_fixture(
         "The capital of France is",
         "The future of AI is",
     ]
-
-    # torchair is only work without chunked-prefill now
-    kwargs = {
-        "ascend_scheduler_config": {
-            "enabled": True,
-        },
-        "refresh": True,
-    }
+    kwargs = {}
+    if not use_v1_schduler:
+        kwargs = {
+            "ascend_scheduler_config": {
+                "enabled": True,
+            },
+            "refresh": True,
+        }
     additional_config.update(**kwargs)
 
     with VllmRunner(
@@ -95,6 +96,15 @@ def test_e2e_deepseekv3_with_torchair_ms_mla():
     _deepseek_torchair_test_fixture(additional_config)
 
 
+def test_e2e_deepseekv3_with_torchair_v1scheduler():
+    additional_config = {
+        "torchair_graph_config": {
+            "enabled": True,
+        },
+    }
+    _deepseek_torchair_test_fixture(additional_config, use_v1_schduler=True)
+
+
 def _pangu_torchair_test_fixture(
     additional_config: Dict,
     *,