ttnn.kv_cache.fill_cache_for_user_

ttnn.kv_cache.fill_cache_for_user_ = Operation(python_fully_qualified_name='ttnn.kv_cache.fill_cache_for_user_', function=<ttnn._ttnn.operations.kv_cache.fill_cache_for_user__t object>, preprocess_golden_function_inputs=<function default_preprocess_golden_function_inputs>, golden_function=None, postprocess_golden_function_outputs=<function default_postprocess_golden_function_outputs>, is_cpp_operation=True, is_experimental=False)

Populates the cache tensor in-place with values sourced from input at batch_index.

Parameters:
  • cache (ttnn.Tensor) – the cache tensor to be written to.

  • input_tensor (ttnn.Tensor) – the input tensor to be written to the cache.

  • batch_index (int) – the index into the cache tensor.

Returns:

ttnn.Tensor – the output tensor.