tf.raw_ops.XlaSparseDenseMatmulPositionalWeightedWithCsrInput 

tf.raw_ops.XlaSparseDenseMatmulPositionalWeightedWithCsrInput(
    row_pointers,
    sorted_sample_ids,
    sorted_token_ids,
    sorted_pos_ids,
    embedding_table,
    weights,
    input_size,
    num_weights,
    num_logical_devices,
    quantization_config_low,
    quantization_config_high,
    quantization_config_num_buckets,
    table_name,
    num_sparsecores_per_device=-1,
    name=None
)

row_pointers A Tensor of type int32.
sorted_sample_ids A Tensor of type int32.
sorted_token_ids A Tensor of type int32.
sorted_pos_ids A Tensor of type int32.
embedding_table A Tensor of type float32.
weights A Tensor of type float32.
input_size An int that is >= 0.
num_weights An int that is >= 0.
num_logical_devices An int that is >= 0.
quantization_config_low A float.
quantization_config_high A float.
quantization_config_num_buckets An int that is >= 0.
table_name A string.
num_sparsecores_per_device An optional int. Defaults to -1.
name A name for the operation (optional).

A tuple of Tensor objects (activations, preserved_received_unique_vectors).
activations A Tensor of type float32.
preserved_received_unique_vectors A Tensor of type float32.