x

app/config.py

@@ -1,10 +1,9 @@
 from functools import lru_cache
-import os
 from typing import Optional
 
 from pydantic import BaseModel
 
-from app.model_catalog import load_catalog, resolve_model_profile, resolve_runtime_settings
+from app.model_catalog import load_app_config
 
 
 class Settings(BaseModel):
@@ -35,35 +34,49 @@ class Settings(BaseModel):
     enable_auto_tool_choice: bool = False
     revision: Optional[str] = None
     api_key: Optional[str] = None
+    quantization: Optional[str] = None
+    model_impl: Optional[str] = None
+    reasoning_parser: Optional[str] = None
+    kv_cache_dtype: Optional[str] = None
+    enable_prefix_caching: bool = False
+    max_num_batched_tokens: int = 0
 
 
 @lru_cache(maxsize=1)
 def get_settings() -> Settings:
-    catalog = load_catalog("config.json")
-    runtime = resolve_runtime_settings(catalog)
-    settings = Settings(
+    config = load_app_config("config.json")
+    return Settings(
         config_file="config.json",
-        model_key=runtime["model_key"],
-        host=runtime["host"],
-        port=runtime["port"],
-        openai_host=runtime["openai_host"],
-        openai_port=runtime["openai_port"],
-        vllm_openai_internal_url=runtime["vllm_openai_internal_url"],
-        public_model_name=runtime["public_model_name"],
-        default_enable_thinking=runtime["default_enable_thinking"],
-        reasoning_enabled=runtime["reasoning_enabled"],
-        model_root=runtime["model_root"],
-        offline_mode=runtime["offline_mode"],
-        api_key=runtime["api_key"],
-        tensor_parallel_size=runtime["tensor_parallel_size"],
-        dtype=runtime["dtype"],
-        revision=runtime["revision"],
+        model_key=config.get("model_key"),
+        selected_model=config.get("selected_model"),
+        model_name=config.get("model_name", ""),
+        served_model_name=config.get("served_model_name"),
+        host=config.get("host", "0.0.0.0"),
+        port=config.get("port", 8000),
+        openai_host=config.get("openai_host", "0.0.0.0"),
+        openai_port=config.get("openai_port", 8001),
+        vllm_openai_internal_url=config.get("vllm_openai_internal_url", "http://127.0.0.1:8001/v1"),
+        public_model_name=config.get("public_model_name", "Qwen_local_model"),
+        default_enable_thinking=config.get("default_enable_thinking", False),
+        reasoning_enabled=config.get("reasoning_enabled", False),
+        model_root=config.get("model_root", "/opt/model"),
+        offline_mode=config.get("offline_mode", True),
+        max_model_len=config.get("max_model_len", 8192),
+        gpu_memory_utilization=config.get("gpu_memory_utilization", 0.92),
+        tensor_parallel_size=config.get("tensor_parallel_size", 2),
+        max_num_seqs=config.get("max_num_seqs", 64),
+        max_tokens=config.get("max_tokens", 4096),
+        dtype=config.get("dtype", "bfloat16"),
+        enforce_eager=config.get("enforce_eager", False),
+        trust_remote_code=config.get("trust_remote_code", False),
+        tool_call_parser=config.get("tool_call_parser"),
+        enable_auto_tool_choice=config.get("enable_auto_tool_choice", False),
+        revision=config.get("revision"),
+        api_key=config.get("api_key"),
+        quantization=config.get("quantization"),
+        model_impl=config.get("model_impl"),
+        reasoning_parser=config.get("reasoning_parser"),
+        kv_cache_dtype=config.get("kv_cache_dtype"),
+        enable_prefix_caching=config.get("enable_prefix_caching", False),
+        max_num_batched_tokens=config.get("max_num_batched_tokens", 0),
     )
-    _, updates, env_vars = resolve_model_profile(
-        content=catalog,
-        requested_model=settings.model_key,
-        requested_tp=settings.tensor_parallel_size,
-    )
-    for key, value in env_vars.items():
-        os.environ[key] = value
-    return settings.model_copy(update=updates | runtime)