[ModelRunner][MultiModal] Remove legacy input mapper/processor from V0 (vllm-project#951)

### What this PR does / why we need it?
Remove legacy input mapper/processor from V0.

Find more details at
vllm-project#673 and
vllm-project/vllm#15686.

### Does this PR introduce _any_ user-facing change?
no.

### How was this patch tested?
Launch online service:

```bash
vllm serve Qwen/Qwen2.5-VL-7B-Instruct \
--dtype bfloat16 \
--max_model_len 32768 \
--max-num-batched-tokens 32768
```

Query the server:

```bash
curl http://localhost:8000/v1/chat/completions \
    -H "Content-Type: application/json" \
    -d '{
    "model": "Qwen/Qwen2.5-VL-7B-Instruct",
    "messages": [
    {"role": "system", "content": "You are a helpful assistant."},
    {"role": "user", "content": [
        {"type": "image_url", "image_url": {"url": "https://modelscope.oss-cn-beijing.aliyuncs.com/resource/qwen.png"}},
        {"type": "text", "text": "What is the text in the illustrate?"}
    ]}
    ]
    }'
```

Result:

```bash
{"id":"chatcmpl-619e70733ed148b3be3a0b6524ee0ef3","object":"chat.completion","created":1748226332,"model":"/home/sss/.cache/modelscope/hub/models/Qwen/Qwen2___5-VL-7B-Instruct","choices":[{"index":0,"message":{"role":"assistant","reasoning_content":null,"content":"The text in the illustration reads \"TONGYI Qwen.\"","tool_calls":[]},"logprobs":null,"finish_reason":"stop","stop_reason":null}],"usage":{"pro
```

Signed-off-by: shen-shanshan <[email protected]>
Co-authored-by: wangxiyuan <[email protected]>
Signed-off-by: wangxiaoxin (A) <[email protected]>

Author: 2 people

vllm_ascend/worker/model_runner.py

@@ -391,7 +391,6 @@ def __init__(self,
         self.sliding_window = self.runner.sliding_window
         self.block_size = self.runner.block_size
         self.enable_lora = self.runner.lora_config is not None
-        self.multi_modal_input_mapper = self.runner.multi_modal_input_mapper
         self.finished_requests_ids = finished_requests_ids
         self.decode_only = True
         self.is_encoder_decoder = self.runner.model_config.is_encoder_decoder
@@ -786,23 +785,15 @@ def _compute_lora_input(self, inter_data: InterDataForSeqGroup,
     def _compute_multi_modal_input(self, inter_data: InterDataForSeqGroup,
                                    seq_group_metadata: SequenceGroupMetadata):
         """If multi-modal data is given, add it to the input."""
-        # NOTE: mm_data only includes the subset of multi-modal items that
+        # NOTE: mm_kwargs only includes the subset of multi-modal items that
         # intersect with the current prefill positions.
         positions = inter_data.input_positions[0]
-        mm_data, placeholder_maps = MultiModalPlaceholderMap.from_seq_group(
+        mm_kwargs, placeholder_maps = MultiModalPlaceholderMap.from_seq_group(
             seq_group_metadata,
             range(positions[0], positions[0] + len(positions)))
-        if not mm_data:
+        if not mm_kwargs:
             return
 
-        if self.runner.mm_registry.has_processor(self.runner.model_config):
-            mm_kwargs = mm_data
-        else:
-            mm_kwargs = self.multi_modal_input_mapper(
-                mm_data,
-                seq_group_metadata.mm_processor_kwargs,
-            )
-
         inter_data.multi_modal_kwargs = mm_kwargs
         inter_data.multi_modal_placeholder_maps = placeholder_maps
 
@@ -918,9 +909,6 @@ def __init__(
         # Multi-modal data support
         self.input_registry = input_registry
         self.mm_registry = mm_registry
-        self.multi_modal_input_mapper = mm_registry \
-            .create_input_mapper(model_config)
-        self.mm_registry.init_mm_limits_per_prompt(self.model_config)
 
         # Lazy initialization
         self.model: nn.Module  # Set after load_model
@@ -1116,8 +1104,8 @@ def profile_run(self) -> None:
 
                 dummy_data = self.input_registry \
                     .dummy_data_for_profiling(self.model_config,
-                                            seq_len,
-                                            self.mm_registry)
+                                              seq_len,
+                                              self.mm_registry)
 
                 seq = SequenceGroupMetadata(
                     request_id=str(group_id),