data_juicer.ops.pipeline.ray_vllm_pipeline module¶ class data_juicer.ops.pipeline.ray_vllm_pipeline.RayVLLMEnginePipeline(*args, **kwargs)[source]¶ Bases: Pipeline Pipeline for Ray vLLM engine. __init__(accelerator_type: str | None = None, *args, **kwargs)[source]¶ Initialization method. :param accelerator_type: The type of accelerator to use (e.g., “V100”, “A100”). Default to None, meaning that only the CPU will be used. Parameters: args – extra args kwargs – extra args run(dataset: Dataset, *, exporter=None, tracer=None, reduce=True) → Dataset[source]¶
