[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/ops/rotary_embedding.py

@@ -21,7 +21,6 @@ import os
 import torch
 import torch_npu
 from vllm.config import get_current_vllm_config
-from vllm.forward_context import get_forward_context
 from vllm.model_executor.layers.rotary_embedding import (
     DeepseekScalingRotaryEmbedding,
     MRotaryEmbedding,
@@ -31,6 +30,7 @@ from vllm.model_executor.layers.rotary_embedding import (
 from vllm.model_executor.layers.rotary_embedding.common import ApplyRotaryEmb
 from vllm.triton_utils import HAS_TRITON
 
+from vllm_ascend.ascend_forward_context import _EXTRA_CTX
 from vllm_ascend.platform import NPUPlatform
 from vllm_ascend.utils import AscendDeviceType, get_ascend_device_type, has_rope, is_vl_model
 
@@ -240,8 +240,8 @@ class AscendRotaryEmbedding(RotaryEmbedding):
         is_neox_style = self.is_neox_style
         if is_neox_style_override is not None:
             is_neox_style = is_neox_style_override
-        is_draft_model = get_forward_context().is_draft_model
-        flash_comm_v1_enabled = get_forward_context().flash_comm_v1_enabled
+        is_draft_model = _EXTRA_CTX.is_draft_model
+        flash_comm_v1_enabled = _EXTRA_CTX.flash_comm_v1_enabled
         if is_draft_model and self.use_mtp and flash_comm_v1_enabled:
             positions = torch.ops.vllm.maybe_all_gather_and_maybe_unpad(positions.contiguous(), True)
         return torch.ops.vllm.npu_rotary_embedding(