[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/multistream/ms_split.py

@@ -223,7 +223,6 @@ def model_input_split_v1_mla_attn(
         attn_mask=attn_mask_pre,
         prefill=prefill_pre,
         decode=decode_pre,
-        with_prefill_across_dp=attn_metadata.with_prefill_across_dp,
     )
     attention_metadata_post = _metadata_cls(
         num_actual_tokens=attn_metadata.num_actual_tokens - token_index,
@@ -240,6 +239,5 @@ def model_input_split_v1_mla_attn(
         attn_state=attn_state_post,
         prefill=prefill_post,
         decode=decode_post,
-        with_prefill_across_dp=attn_metadata.with_prefill_across_dp,
     )
     return [attention_metadata_pre, attention_metadata_post]