Qwen_local_model

app/config.py

@@ -17,6 +17,7 @@ class Settings(BaseModel):
     port: int = 8000
     openai_host: str = "0.0.0.0"
     openai_port: int = 8001
+    public_model_name: str = "Qwen_local_model"
     model_root: str = "/opt/model"
     offline_mode: bool = True
     max_model_len: int = 8192
@@ -44,6 +45,7 @@ def get_settings() -> Settings:
         port=runtime["port"],
         openai_host=runtime["openai_host"],
         openai_port=runtime["openai_port"],
+        public_model_name=runtime["public_model_name"],
         model_root=runtime["model_root"],
         offline_mode=runtime["offline_mode"],
         api_key=runtime["api_key"],

app/model_catalog.py

@@ -68,6 +68,7 @@ def resolve_runtime_settings(content: dict[str, Any]) -> dict[str, Any]:
         "port": _to_int(api_service.get("port"), 8000),
         "openai_host": str(openai_service.get("host", "0.0.0.0")),
         "openai_port": _to_int(openai_service.get("port"), 8001),
+        "public_model_name": _to_str(content.get("public_model_name"), "Qwen_local_model"),
         "api_key": str(content.get("api_key", "")).strip() or None,
         "tensor_parallel_size": _to_int(content.get("tensor_parallel_size"), 2),
         "dtype": str(content.get("dtype", "bfloat16")),

app/start_openai.py

@@ -18,6 +18,7 @@ def build_command() -> list[str]:
         os.environ[key] = value
     host = str(runtime["openai_host"])
     port = str(runtime["openai_port"])
+    public_model_name = str(runtime["public_model_name"]).strip()
     api_key = runtime["api_key"] or ""
     dtype = str(updates["dtype"] or runtime["dtype"])
     quantization = str(updates["quantization"] or "").strip()
@@ -33,7 +34,7 @@ def build_command() -> list[str]:
         "--model",
         str(updates["model_name"]),
         "--served-model-name",
-        str(updates["served_model_name"]),
+        public_model_name or str(updates["served_model_name"]),
         "--tensor-parallel-size",
         str(updates["tensor_parallel_size"]),
         "--max-model-len",