[Feature] support aclgraph for model runner v2 (#7110)

### What this PR does / why we need it?
This PR aims to support aclgraph for model runner v2, please see RFC
#5208. The PR contains these modifications:
- adapt to newest commit of vllm main branch.
- supply a unified interface of extra forward context for both model
runner v1 and model runner v2.
- implement graph mode for main model. 

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

### How was this patch tested?

- vLLM version: v0.16.0
- vLLM main:
4034c3d32e

---------

Signed-off-by: Ronald1995 <ronaldautomobile@163.com>

vllm_ascend/compilation/acl_graph.py

@@ -19,6 +19,8 @@ from vllm.forward_context import BatchDescriptor, get_forward_context
 from vllm.logger import logger
 from vllm.platforms import current_platform
 
+from vllm_ascend.ascend_forward_context import _EXTRA_CTX
+
 from ..utils import weak_ref_tensors
 
 
@@ -195,7 +197,7 @@ class ACLGraphWrapper:
             if self.vllm_config.speculative_config
             else False
         )
-        if self.runtime_mode != CUDAGraphMode.FULL or not forward_context.is_draft_model or not use_eagle:
+        if self.runtime_mode != CUDAGraphMode.FULL or not _EXTRA_CTX.is_draft_model or not use_eagle:
             torch.npu.current_stream().synchronize()
         entry.aclgraph.replay()
         return entry.output