main add ascend scheduler support multimodal (#2844)

### What this PR does / why we need it?
On main, AscendScheduler does not support Multimodels, becuse of lacking
of scheduled_encoder_inputs which is need on multimodels inference

### Does this PR introduce _any_ user-facing change?

No

### How was this patch tested?
vLLM version: main@93e28e6862669e3b5cf47cea9f782a65ec47e155

- vLLM version: v0.10.2rc2
- vLLM main:
15b8fef453

---------

Signed-off-by: fan2956 <zhoufan53@huawei.com>
Co-authored-by: zhoufan2956 <zhoufan2956@163.com>

tests/ut/core/test_schedule_config.py

@@ -75,13 +75,6 @@ class TestAscendSchedulerConfig(TestBase):
             str(context.exception),
         )
 
-    def test_not_implemented_multimodal(self):
-        with self.assertRaises(NotImplementedError) as context:
-            AscendSchedulerConfig.initialize_from_config(
-                SchedulerConfig(is_multimodal_model=True), {})
-        self.assertIn("currently AscendScheduler only supports LLM models",
-                      str(context.exception))
-
     def test_not_implemented_send_delta_data(self):
         with self.assertRaises(NotImplementedError) as context:
             AscendSchedulerConfig.initialize_from_config(
@@ -118,6 +111,11 @@ class TestAscendSchedulerConfig(TestBase):
         self.assertEqual(ascend_config.max_num_encoder_input_tokens, 8192)
         self.assertEqual(ascend_config.encoder_cache_size, 8192)
 
+    def test_valid_config_with_multimodal(self):
+        config = AscendSchedulerConfig.initialize_from_config(
+            SchedulerConfig(is_multimodal_model=True), {})
+        self.assertTrue(config.is_multimodal_model)
+
     def test_valid_config_with_chunked_prefill(self):
         ascend_config = AscendSchedulerConfig.initialize_from_config(
             self.basic_scheduler_config,