[main][refactor] Refactoring forward_context and model_runner_v1 (#1979)

### What this PR does / why we need it?

A refactoring of forward_context and model_runner_v1, add some context
which is necessary in model inference into forward_context, and refactor
dummy_run logic, make it more reasonable.
Some details for this PR:

Add `ascend_forward_context`;
Update mc2_v2 op, and support `active_mask` param;
Update scripts in examples dir;
refactor `dummy_run` logic;
Add soc_version for A2 and A3;

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

No change at user-facing.

### How was this patch tested?


- vLLM version: v0.10.0
- vLLM main:
57c22e57f9

Signed-off-by: zzzzwwjj <1183291235@qq.com>

vllm_ascend/torchair/torchair_worker.py

@@ -52,13 +52,3 @@ class NPUTorchairWorker(NPUWorker):
         self.model_runner.new_kv_cache_bytes = available_kv_cache_memory
 
         return available_kv_cache_memory
-
-    def _get_max_num_tokens_and_with_prefill(self):
-        """Override _get_max_num_tokens_and_with_prefill to update max_num_tokens."""
-
-        max_num_tokens, with_prefill = super(
-        )._get_max_num_tokens_and_with_prefill()
-        if not with_prefill:
-            max_num_tokens = self.model_runner.select_torchair_padded_batch_size(
-                max_num_tokens)
-        return max_num_tokens, with_prefill