Python function

unflatten_ragged_attention_inputs

unflatten_ragged_attention_inputs()

max.nn.kv_cache.unflatten_ragged_attention_inputs(kv_inputs_flat, *, n_devices)

source

Unmarshals flattened KV graph inputs into typed cache values.

Parameters:

• kv_inputs_flat (Sequence[Any]) – Flattened graph values for all KV inputs. Elements may be Value instances or Tensor-like objects with a _graph_value attribute.
• n_devices (int) – Number of devices represented in kv_inputs_flat.

Return type:

list[PagedCacheValues]

Was this page helpful?

Thank you! We'll create more content like this.

Thank you for helping us improve!

😔 What went wrong?

Some code doesn’t work

It includes inaccurate information

It's missing information I need

It was difficult to understand

Other

Submit