Merge branch 'wanglong3-v0.9.2-dev-patch-69158' into 'v0.9.2-dev'

Remove print.

See merge request dcutoolkit/deeplearing/vllm!356

vllm/model_executor/layers/fused_moe/fused_moe.py

@@ -13,6 +13,7 @@ import vllm.envs as envs
 import vllm.model_executor.layers.fused_moe.modular_kernel as mk
 from vllm import _custom_ops as ops
 from vllm.logger import init_logger
+logger = init_logger(__name__)
 # yapf: disable
 from vllm.model_executor.layers.fused_moe.config import (
     FusedMoEQuantConfig, get_config_quant_dtype)
@@ -31,7 +32,7 @@ try:
     from lmslim.layers.fused_moe.fuse_moe_int8 import (fused_experts_impl_int8, get_w8a8moe_json)
     from lmslim.layers.fused_moe.fuse_moe_w4a8 import fused_experts_impl_w4a8
 except Exception:
-    print("INFO: Please install lmslim if you want to infer the quantitative model of moe.\n") 
+    logger.warning_once("Please install lmslim if you want to infer the quantitative model of moe.")
 
 from vllm.model_executor.layers.fused_moe.prepare_finalize import (
     MoEPrepareAndFinalizeNoEP)
@@ -43,9 +44,6 @@ from vllm.utils import direct_register_custom_op
 
 # from .rocm_aiter_fused_moe import is_rocm_aiter_moe_enabled
 
-
-logger = init_logger(__name__)
-
 if envs.VLLM_USE_GLOBAL_CACHE13:
     moe_cache_singleton = None