[Core] Fix block table shape to make Prefix cache work with Ascend scheduler (#1446)

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

This fix the shape of block_table which was introduced by hybrid kv
groups several weeks ago.

Error will be raised when enable prefix-cache (eager or not) and Ascend
Scheduler at the same time, just send two identical requests and it will
reproduce.

v0.9.1: https://github.com/vllm-project/vllm-ascend/pull/1297

### Does this PR introduce _any_ user-facing change?
No

### How was this patch tested?
Test manually

Signed-off-by: Yizhou Liu <liu_yizhou@outlook.com>

vllm_ascend/attention/attention_v1.py

@@ -355,11 +355,13 @@ class AscendAttentionBackendImpl(AttentionImpl):
                 assert attn_metadata is not None
                 assert attn_metadata.attn_mask is not None
                 compress_mask = attn_metadata.attn_mask
+                batch_size = attn_metadata.query_lens.shape[0]
+                block_table = attn_metadata.block_tables[:batch_size, :]
                 torch_npu._npu_flash_attention_qlens(
                     query=query,
                     key_cache=self.key_cache,
                     value_cache=self.value_cache,
-                    block_table=attn_metadata.block_tables,
+                    block_table=block_table,
                     mask=compress_mask,
                     seq_len=attn_metadata.query_lens,
                     context_lens=attn_metadata.seq_lens,