面向 AI 工作负载的高性能、多模态原生引擎

import vane
vane.configure(runner="ray")
con = vane.connect()


assets = con.sql("""
    SELECT asset_id, uri, media_type
    FROM read_parquet('s3://raw-assets/*.parquet')
    WHERE media_type IN ('image', 'video', 'audio')
""")


features = assets.map_batches(
    DecodeAndInfer,  # user UDF; 1 model load/actor
    schema=feature_schema,  # explicit user schema
    gpus=1,
    actor_number=4,
)


features.write_parquet("s3://model-ready/features/")