[Misc] Clean up uesless code in attention (#1933)

Before do attention module refactor, we can do some code cleanup to make
the next step easier.

What this PR does:

1. remove uesless `common_prefix_len` for attention builder
2. remove uesless `is_only_prefill` and `num_input_tokens` in attention
metadata.
3. remove `CommonAttentionMetadata` and ues `query_start_loc` instead,
`CommonAttentionMetadata` is over designed and uesless
4. update the attention backend input parameters to keep the same as
vLLM.
5. Rename attention name to the same style with `ASCEND` prefix

- vLLM version: v0.9.2
- vLLM main:
107111a859

Signed-off-by: wangxiyuan <wangxiyuan1007@gmail.com>

vllm_ascend/worker/eagle_proposer_v1.py

@@ -132,7 +132,6 @@ class EagleProposer:
             num_reqs=batch_size,
             num_actual_tokens=num_tokens,
             max_query_len=max_query_len,
-            common_prefix_len=0,
         )
         if self.use_cuda_graph and \
             num_tokens <= self.cudagraph_batch_sizes[-1]: