[Main2Main] Upgrade vllm commit to 0105 (#5595)

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

Upgrade vllm commit to 0105 (8be6432bdaf6275664d857b1e5e9bf8ed1ce299e)

1. Remove `maybe_padded_num_tokens` arg in `model_runner_v1.py` since
https://github.com/vllm-project/vllm/pull/31517 deleted unused arg

2. Remove dense `Qwen/Qwen3-0.6B` in
`tests/e2e/multicard/test_aclgraph_capture_replay.py` and
`tests/e2e/multicard/test_data_parallel.py` due to
https://github.com/vllm-project/vllm/pull/30739
where offline data parallel mode will not be supported/useful for dense
models

3. Adapt `vllm_ascend/worker/worker.py` due to
https://github.com/vllm-project/vllm/pull/31584

4. Adapt `self.block_size` calling due to
https://github.com/vllm-project/vllm/pull/31540

5. Modify `test_mla_v1.py` due to
https://github.com/vllm-project/vllm/pull/28454 , which refactorred
`get_head_size()`

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

### How was this patch tested?

- vLLM version: v0.13.0
- vLLM main:
7157596103

Signed-off-by: wjunLu <wjunlu217@gmail.com>

vllm_ascend/spec_decode/eagle_proposer.py

@@ -136,6 +136,7 @@ class EagleProposer(VllmEagleProposer):
         draft_attn_layer_names = draft_attn_layer_names - draft_indexer_layer_names
         assert len(draft_attn_layer_names) == 1
         self.attn_layer_name = list(draft_attn_layer_names)
+        self.attn_layer_names = self.attn_layer_name
 
         # share embed_tokens with the target model if needed
         if get_pp_group().world_size == 1:
@@ -442,14 +443,19 @@ class EagleProposer(VllmEagleProposer):
             # For the requests that exceed the max model length, we set the
             # TODO: sequence length to 1 to minimize their overheads in attention.
 
+            if self.attn_metadata_builder is None:
+                attn_metadata_builder = self._get_attention_metadata_builder()
+            else:
+                attn_metadata_builder = self.attn_metadata_builder
+            block_size = attn_metadata_builder.kv_cache_spec.block_size
+
             # Compute the slot mapping.
-            block_numbers = (clamped_positions // self.block_size)
+            block_numbers = (clamped_positions // block_size)
             block_ids = attn_metadata.block_tables.gather(
                 dim=1, index=block_numbers.view(-1, 1))
             block_ids = block_ids.view(-1)
-            slot_mapping_tmp = (
-                block_ids * self.vllm_config.cache_config.block_size +
-                clamped_positions % self.block_size)
+            slot_mapping_tmp = (block_ids * block_size +
+                                clamped_positions % block_size)
 
             # Mask out the slot mappings that exceed the max model length.
             # Otherwise, the KV cache will be inadvertently updated with the