[Feature] Support to use fullgraph with eagle (#5118)

### What this PR does / why we need it?
    
We support to use full graph with eagle. 

Change list:
1. Distinguish between processing graph_params and draft_graph_params in
attention_v1.
    2. Adapt the full-graph mode in eagle_proposer, include:
        1). If use full graph, make Fullgraph Wrapper when load model.
2). Build a new meatadata, set running mode in FULL and mark attention
update in dummy_run when in Fullgraph mode.
3). Fixed and fill any attn_metadata, such as
attn_metadata.slot_mapping.
        4). Add a descriptor.
        5). Set running mode and triggered update metadata.
3. Trans is_mtp_model to is_draft_model, and add the update of
workspace.

NOTE:
When set async_scheduling=True, the draft model will enforce execution
in eager mode.

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

### How was this patch tested?

- vLLM version: v0.12.0
- vLLM main:
ad32e3e19c

---------

Signed-off-by: anon189Ty <Stari_Falcon@outlook.com>
Co-authored-by: Yizhou Liu <liu_yizhou@outlook.com>
Co-authored-by: Yizhou <136800916+yiz-liu@users.noreply.github.com>

vllm_ascend/spec_decode/mtp_proposer.py

@@ -303,7 +303,7 @@ class MtpProposer(Proposer):
                     num_actual_tokens=0,
                     aclgraph_runtime_mode=aclgraph_runtime_mode,
                     batch_descriptor=batch_descriptor,
-                    is_mtp_model=True,
+                    is_draft_model=True,
                     in_profile_run=is_profile):
                 if self.enable_shared_expert_dp:
                     positions = positions.unsqueeze(-1)
@@ -782,7 +782,7 @@ class MtpProposer(Proposer):
                     aclgraph_runtime_mode=aclgraph_runtime_mode,
                     batch_descriptor=batch_descriptor,
                     num_actual_tokens=num_tokens,
-                    is_mtp_model=True):
+                    is_draft_model=True):
                 with ProfileExecuteDuration().capture_async('mtp_forward'):
                     model_kwargs = {}
                     model_kwargs["attn_metadata"] = attn_metadata