add custom scheduler guide and performance env

Signed-off-by: MengqingCao <[email protected]>
Signed-off-by: Yikun Jiang <[email protected]>

Author: MengqingCao

docs/source/quick_start.md

@@ -139,4 +139,8 @@ INFO:     Application shutdown complete.
 
 Finally, you can exit container by using `ctrl-D`.
 ::::
-:::::
+:::::
+
+### Performance enhancement related environment variables in Mindie Turbo
+
+Currently, some performance enhancement features in MindIE Turbo have certain scenario restrictions. For these features, environment variables are used to control whether to enable them. For related environment variables, see its [official documentation](https://www.hiascend.com/document/detail/zh/mindie/20RC1/AcceleratePlugin/turbodev/mindie-turbo-0010.html).

docs/source/user_guide/suppoted_features.md

@@ -35,3 +35,4 @@ MindIE Turbo is an optional performace optimization plugin. Find more informatio
 | Graph Mode                    | 🟡 Planned     | 🟡 Planned     | Will support in v0.8.x                                                 |
 | Sleep Mode                    | 🟢 Functional  | 🟢 Functional  | [Usage Limits][#733](https://github.com/vllm-project/vllm-ascend/issues/733) |
 | MTP                           | 🟢 Functional  | 🟢 Functional  | [Usage Limits][#734](https://github.com/vllm-project/vllm-ascend/issues/734) |
+| Custom Scheduler              | 🟢 Functional  | 🟢 Functional  | [Usage Limits][#788](https://github.com/vllm-project/vllm-ascend/issues/788) |

vllm_ascend/utils.py

@@ -32,4 +32,4 @@ def try_register_lib(lib_name: str,
             if lib_info:
                 logger.info(lib_info)
     except Exception:
-        logger.warning_once(exception_info)
+        logger.info_once(exception_info)

vllm_ascend/worker/worker.py

@@ -78,7 +78,7 @@ def __init__(
         try_register_lib(
             "mindie_turbo",
             "MindIE Turbo is installed. vLLM inference will be accelerated with MindIE Turbo.",
-            "MindIE Turbo not found, please check the installation of mindie-turbo if you attempt to use it."
+            "MindIE Turbo not found or unable to `import mindie_turbo`, skip MindIE Turbo acceleration."
         )
         # distribute related config
         self.parallel_config.rank = rank

vllm_ascend/worker/worker_v1.py

@@ -78,7 +78,7 @@ def __init__(self,
         try_register_lib(
             "mindie_turbo",
             "MindIE Turbo is installed. vLLM inference will be accelerated with MindIE Turbo.",
-            "MindIE Turbo not found, please check the installation of mindie-turbo if you attempt to use it."
+            "MindIE Turbo not found or unable to `import mindie_turbo`, skip MindIE Turbo acceleration."
         )
 
         if self.cache_config.cache_dtype == "auto":