x

app/model_catalog.py

@@ -0,0 +1,66 @@
+import json
+from pathlib import Path
+from typing import Any
+
+
+def _to_bool(value: Any, default: bool) -> bool:
+    if isinstance(value, bool):
+        return value
+    if isinstance(value, str):
+        normalized = value.strip().lower()
+        if normalized in {"true", "1", "yes", "y"}:
+            return True
+        if normalized in {"false", "0", "no", "n"}:
+            return False
+    return default
+
+
+def _to_int(value: Any, default: int) -> int:
+    try:
+        return int(value)
+    except (TypeError, ValueError):
+        return default
+
+
+def _to_float(value: Any, default: float) -> float:
+    try:
+        return float(value)
+    except (TypeError, ValueError):
+        return default
+
+
+def resolve_model_profile(
+    catalog_path: str, requested_model: str | None, requested_tp: int
+) -> tuple[str, dict[str, Any], dict[str, str]]:
+    content = json.loads(Path(catalog_path).read_text(encoding="utf-8"))
+    if not isinstance(content, dict):
+        raise ValueError("config.json must be a JSON object")
+    default_model = content.get("default_model")
+    profiles = {k: v for k, v in content.items() if k != "default_model"}
+    model_key = requested_model or default_model
+    if not model_key or model_key not in profiles:
+        raise ValueError(f"model profile '{model_key}' not found in config.json")
+    profile = profiles[model_key]
+    if not isinstance(profile, dict):
+        raise ValueError(f"model profile '{model_key}' must be a JSON object")
+    valid_tp_raw = profile.get("valid_tp", [])
+    valid_tp = [_to_int(item, 0) for item in valid_tp_raw if _to_int(item, 0) > 0]
+    resolved_tp = requested_tp
+    if valid_tp and resolved_tp not in valid_tp:
+        resolved_tp = valid_tp[0]
+    updates = {
+        "selected_model": model_key,
+        "model_name": profile.get("hf_model_id", model_key),
+        "served_model_name": profile.get("served_model_name", model_key),
+        "max_model_len": _to_int(profile.get("ctx"), 8192),
+        "max_num_seqs": _to_int(profile.get("max_num_seqs"), 64),
+        "max_tokens": _to_int(profile.get("max_tokens"), 4096),
+        "gpu_memory_utilization": _to_float(profile.get("gpu_util"), 0.92),
+        "trust_remote_code": _to_bool(profile.get("trust_remote"), False),
+        "enforce_eager": _to_bool(profile.get("enforce_eager"), False),
+        "tensor_parallel_size": resolved_tp,
+        "tool_call_parser": profile.get("tool_call_parser"),
+        "enable_auto_tool_choice": _to_bool(profile.get("enable_auto_tool_choice"), False),
+    }
+    env_vars = {str(k): str(v) for k, v in dict(profile.get("env", {})).items()}
+    return model_key, updates, env_vars