[Bugfix] fix logging and d2h bug for flash comm1 (#3505)

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

Fix 3 bugs in flash comm1 of Allgather
EP(https://github.com/vllm-project/vllm-ascend/pull/3334):
1. call `enable_sp()` with argument `vllm_config` trigger a lot of
warning log, this PR caches its return value.
2. `num_tokens_after_padding` should be cpu tensor as it will used as
`num_tokens_across_dp_cpu` in `DPMetadata`. It will causes may d2h copy
when running model.
3. In PD, model runner will execute `kv_connector_no_forward`，where
`num_tokens` is None

- vLLM version: v0.11.0rc3
- vLLM main: https://github.com/vllm-project/vllm/commit/v0.11.0

---------

Signed-off-by: realliujiaxu <realliujiaxu@163.com>

vllm_ascend/ascend_forward_context.py

@@ -114,7 +114,7 @@ def set_ascend_forward_context(
         # the performance may degrade due to the switching of communication methods.
         if is_moe_model(vllm_config):
             sp_enabled = enable_sp(vllm_config) and \
-                tp_world_size > 1
+                tp_world_size > 1 and num_tokens is not None
         else:
             sp_enabled = enable_sp(vllm_config) and \
                 tp_world_size > 1 and \