tf.raw_ops.XlaSparseDenseMatmulPositionalWeightedGradWithAdagradAndCsrInput 

tf.raw_ops.XlaSparseDenseMatmulPositionalWeightedGradWithAdagradAndCsrInput(
    row_pointers,
    sorted_sample_ids,
    sorted_token_ids,
    sorted_pos_ids,
    activation_gradients,
    preserved_received_unique_vectors,
    preserved_weights,
    embedding_table,
    embedding_table_accumulator,
    embedding_table_learning_rate,
    weights,
    hyperparameters,
    num_weights,
    custom_computation,
    quantization_config_low,
    quantization_config_high,
    quantization_config_num_buckets,
    table_name,
    clip_weight_min=float('-inf'),
    clip_weight_max=float('inf'),
    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.
activation_gradients A Tensor of type float32.
preserved_received_unique_vectors A Tensor of type float32.
preserved_weights A Tensor of type float32.
embedding_table A Tensor of type float32.
embedding_table_accumulator A Tensor of type float32.
embedding_table_learning_rate A Tensor of type float32.
weights A list of at least 1 Tensor objects with type float32.
hyperparameters A list of Tensor objects with type float32.
num_weights An int that is >= 0.
custom_computation A function decorated with @Defun.
quantization_config_low A float.
quantization_config_high A float.
quantization_config_num_buckets An int that is >= 0.
table_name A string.
clip_weight_min An optional float. Defaults to float('-inf').
clip_weight_max An optional float. Defaults to float('inf').
num_sparsecores_per_device An optional int. Defaults to -1.
name A name for the operation (optional).

A tuple of Tensor objects (updated_embedding_table, updated_embedding_table_accumulator, updated_weights).
updated_embedding_table A Tensor of type float32.
updated_embedding_table_accumulator A Tensor of type float32.
updated_weights A list with the same length as weights of Tensor objects with type float32.