reset default block_size from 16 to 128 (#84)

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

Changed default block_size in platform.py from 16 to 128, as Ascend
Devices have a better affinity for block size 128.

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

### How was this patch tested?
CI passed

Signed-off-by: hzji210@gmail.com <hzji210@gmail.com>

vllm_ascend/platform.py

@@ -96,7 +96,7 @@ class NPUPlatform(Platform):
             parallel_config.worker_cls = "vllm_ascend.worker.NPUWorker"
         cache_config = vllm_config.cache_config
         if cache_config and cache_config.block_size is None:
-            cache_config.block_size = 16
+            cache_config.block_size = 128
 
     @classmethod
     def get_attn_backend_cls(cls, selected_backend, head_size, dtype,