[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/models/pangu_moe.py

@@ -837,12 +837,8 @@ class PanguProMoEModel(nn.Module):
             # if attn_meatadata is not passed, we try to get it from forward_context.
             if attn_metadata is None:
                 attn_metadata = get_forward_context().attn_metadata
-            if attn_metadata is None:
-                # when attn_meatadata is None, it is in profile_run. num_tokens on all dp ranks
-                # are same.
-                max_tokens_across_dp = hidden_states.shape[0]
-            else:
-                max_tokens_across_dp = attn_metadata.max_num_tokens_across_dp
+
+            max_tokens_across_dp = get_forward_context().max_tokens_across_dp
 
             tp_size = get_tp_group().world_size
             # reduce scatter will split the input tensor into equal sizes and then scatter them on all ranks.