fix bug when max_seqs=14 in mtp=2 scenario and raise error when cudagraph_capture_sizes can't be an integer multiple of uniform_decode_query_len (#3909)

### What this PR does / why we need it?
1. Revert [bugfix for mtp in
fullgraph](0948483642)
and support it when vllm supports
2. raise error when cudagraph_capture_sizes can't be an integer multiple
of uniform_decode_query_len
3. bugfix when max_num_seqs=14 in mtp=2 scenario

---------

Signed-off-by: zouyida2052 <zouyida2002@gmail.com>

vllm_ascend/platform.py

@@ -263,7 +263,6 @@ class NPUPlatform(Platform):
             **********************************************************************************\033[0m
             """
             logger.warning(warning_message)
-            update_aclgraph_sizes(vllm_config)
         else:
             logger.info(
                 "%s cudagraph_mode is not support on NPU. falling back to NONE",