@basetenlabs/client - v0.2.0
    Preparing search index...

    Interface ModelTRTQuantizationConfiguration

    Configuration for quantization of TRT models

    Args: calib_size (int, optional): Size of calibration dataset. Defaults to 1024. recommended to increase for production runs (e.g. 1536), or decrease e.g. to 256 for quick testing. calib_dataset (str, optional): Hugginface dataset to use for calibration. Defaults to 'cnn_dailymail'. uses split='train' and quantized based on 'text' column. calib_max_seq_length (int, optional): Maximum sequence length for calibration. Defaults to 2048.

    interface ModelTRTQuantizationConfiguration {
        calib_dataset?: string;
        calib_max_seq_length?: number;
        calib_size?: number;
        [k: string]: unknown;
    }

    Indexable

    • [k: string]: unknown
    Index
    calib_dataset?: string
    calib_max_seq_length?: number
    calib_size?: number