[bugfix] Fix warning bug: model config is None. (#3238)

Cleanup wrong warning log error: model config is None

- vLLM version: v0.10.2
- vLLM main:
https://github.com/vllm-project/vllm/commit/releases/v0.11.0

---------

Signed-off-by: weijinqian_v1 <weijinqian@huawei.com>
Co-authored-by: weijinqian_v1 <weijinqian@huawei.com>

vllm_ascend/ascend_forward_context.py

@@ -106,7 +106,7 @@ def set_ascend_forward_context(
         # Currently, it is an empirical value. In normal scenarios, if the concurrency exceeds this threshold,
         # the performance benefits can be maximized. Conversely, if the concurrency is below the threshold,
         # the performance may degrade due to the switching of communication methods.
-        sp_enabled = enable_sp() and \
+        sp_enabled = enable_sp(vllm_config) and \
             tp_world_size > 1 and \
             num_tokens is not None and num_tokens > 1000
 

vllm_ascend/utils.py

@@ -597,11 +597,12 @@ def dense_optim_enable() -> bool:
     return envs_ascend.VLLM_ASCEND_ENABLE_DENSE_OPTIMIZE
 
 
-def enable_sp() -> bool:
-    from vllm.config import get_cached_compilation_config
-
+def enable_sp(vllm_config=None) -> bool:
+    if vllm_config is None:
+        from vllm.config import get_current_vllm_config
+        vllm_config = get_current_vllm_config()
     return (
-        get_cached_compilation_config().pass_config.enable_sequence_parallelism
+        vllm_config.compilation_config.pass_config.enable_sequence_parallelism
         or envs_ascend.VLLM_ASCEND_ENABLE_FLASHCOMM)