[Bugfix] Add missing draft_attn_metadatas parameter to fix MTP test (#6232)

### What this PR does / why we need it?

Fix the MTP test failure caused by accessing non-existent attribute
`forward_context.draft_attn_metadatas`.

**Root cause:**
In `AscendAttentionBackendImpl.update_graph_params`, the code
incorrectly accessed `forward_context.draft_attn_metadatas`, but
`ForwardContext` class doesn't have this attribute. The original code
passed this value via function parameter.

**Fix:**
Add `draft_attn_metadatas` parameter to the entire call chain:
- `update_full_graph_params` function in `acl_graph.py`
- All `update_graph_params` methods in attention backends
- Pass the parameter correctly in `eagle_proposer.py`

Also applied Gemini's suggestion to make `vllm_config=None` in
`AscendAttentionCPImpl.update_graph_params` for API consistency.

Related to item 9 in #5463

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

No.

### How was this patch tested?

This fixes the CI test failure:

`test_deepseek_mtp_correctness[True-FULL_DECODE_ONLY-2-wemaster/deepseek_mtp_main_random_bf16]`

Signed-off-by: lico67373 <918688502@qq.com>

vllm_ascend/attention/attention_v1.py

@@ -379,6 +379,7 @@ class AscendAttentionBackendImpl(AttentionImpl):
         vllm_config,
         speculative_config=None,
         num_dcp_pcp_tokens=None,
+        draft_attn_metadatas=None,
     ):
         if using_paged_attention(num_tokens, vllm_config):
             # Paged Attention update logic
@@ -436,7 +437,7 @@ class AscendAttentionBackendImpl(AttentionImpl):
             # FIA update logic
             if forward_context.is_draft_model:
                 graph_params = get_draft_graph_params()
-                attn_metadata = forward_context.draft_attn_metadatas
+                attn_metadata = draft_attn_metadatas
                 attn_keys = list(attn_metadata[0].keys())
             else:
                 graph_params = get_graph_params()

vllm_ascend/attention/context_parallel/attention_cp.py

@@ -281,9 +281,10 @@ class AscendAttentionCPImpl(AscendAttentionBackendImpl):
         update_stream,
         forward_context,
         num_tokens,
-        vllm_config,
+        vllm_config=None,
         speculative_config=None,
         num_dcp_pcp_tokens=None,
+        draft_attn_metadatas=None,
     ):
         graph_params = get_graph_params()
         # FIXME: Behold! We are using a temporary hack here to update the args

vllm_ascend/attention/context_parallel/mla_cp.py

@@ -292,6 +292,7 @@ class AscendMlaCPImpl(AscendMLAImpl):
         vllm_config=None,
         speculative_config=None,
         num_dcp_pcp_tokens=None,
+        draft_attn_metadatas=None,
     ):
         if forward_context.is_draft_model:
             graph_params = get_draft_graph_params()

vllm_ascend/attention/mla_v1.py

@@ -733,6 +733,7 @@ class AscendMLAImpl(MLAAttentionImpl):
         vllm_config=None,
         speculative_config=None,
         num_dcp_pcp_tokens=None,
+        draft_attn_metadatas=None,
     ):
         if forward_context.is_draft_model:
             graph_params = get_draft_graph_params()