Function validate_args

fastdeploy/benchmarks/throughput.py:223–303

Validate command-line arguments.

(args)

def validate_args(args):
    """
    Validate command-line arguments.
    """

    # === Deprecation and Defaulting ===
    if args.dataset is not None:
        warnings.warn(
            "The '--dataset' argument will be deprecated in the next release. "
            "Please use '--dataset-name' and '--dataset-path' instead.",
            stacklevel=2,
        )
        args.dataset_path = args.dataset

    if not getattr(args, "tokenizer", None):
        args.tokenizer = args.model

    # === Backend Validation ===
    valid_backends = {"fastdeploy", "hf", "fastdeploy-chat"}
    if args.backend not in valid_backends:
        raise ValueError(f"Unsupported backend: {args.backend}")

    # === Dataset Configuration ===
    if not args.dataset and not args.dataset_path:
        print("When dataset path is not set, it will default to random dataset")
        args.dataset_name = "random"
        if args.input_len is None:
            raise ValueError("input_len must be provided for a random dataset")

    # === Dataset Name Specific Checks ===
    # --hf-subset and --hf-split: only used
    # when dataset_name is 'hf'
    if args.dataset_name != "hf" and (
        getattr(args, "hf_subset", None) is not None or getattr(args, "hf_split", None) is not None
    ):
        warnings.warn(
            "--hf-subset and --hf-split will be ignored \
                since --dataset-name is not 'hf'.",
            stacklevel=2,
        )
    # elif args.dataset_name == "hf":
    #     if args.dataset_path in (
    #             VisionArenaDataset.SUPPORTED_DATASET_PATHS.keys()
    #             | ConversationDataset.SUPPORTED_DATASET_PATHS):
    #         assert args.backend == "vllm-chat", f"{args.dataset_path} needs to use vllm-chat as the backend."  #noqa: E501
    #     elif args.dataset_path in (InstructCoderDataset.SUPPORTED_DATASET_PATHS
    #                                | AIMODataset.SUPPORTED_DATASET_PATHS):
    #         assert args.backend == "vllm", f"{args.dataset_path} needs to use vllm as the backend."  #noqa: E501
    #     else:
    #         raise ValueError(
    #             f"{args.dataset_path} is not supported by hf dataset.")

    # --random-range-ratio: only used when dataset_name is 'random'
    if args.dataset_name != "random" and args.random_range_ratio is not None:
        warnings.warn(
            "--random-range-ratio will be ignored since \
                --dataset-name is not 'random'.",
            stacklevel=2,