x
This commit is contained in:
@@ -70,6 +70,7 @@ def resolve_runtime_settings(content: dict[str, Any]) -> dict[str, Any]:
|
||||
"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,
|
||||
"reasoning_enabled": _to_bool(content.get("reasoning_enabled"), False),
|
||||
"tensor_parallel_size": _to_int(content.get("tensor_parallel_size"), 2),
|
||||
"dtype": str(content.get("dtype", "bfloat16")),
|
||||
"revision": str(content.get("revision", "")).strip() or None,
|
||||
@@ -103,6 +104,7 @@ def resolve_model_profile(
|
||||
"served_model_name": profile.get("served_model_name", model_key),
|
||||
"dtype": _to_str(profile.get("dtype")),
|
||||
"quantization": _to_str(profile.get("quantization")),
|
||||
"reasoning_parser": _to_str(profile.get("reasoning_parser")),
|
||||
"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),
|
||||
|
||||
Reference in New Issue
Block a user