IMPORTANT: To view this page as Markdown, append `.md` to the URL (e.g. /get-started.md). For the complete documentation index, see llms.txt.
Skip to main content
For the complete documentation index, see llms.txt. Markdown versions of all pages are available by appending .md to any URL (e.g. /get-started.md).

Python function

decoder_outputs

decoder_outputs()​

max.pipelines.lib.registration_graph_api.decoder_outputs(outputs, *, state=())

source

Returns a graph-API text model’s grouped outputs as the role’s.

A graph-API text model names its outputs by group, as logits_outputs() does; a registered decoder that delegates to one returns them through this.

Parameters:

  • outputs (DecoderOutputs) – The model’s grouped outputs.
  • state (Sequence[TensorValue]) – The per-request state the decoder returns for its next step, in the order its store declares.

Raises:

ValueError – If the outputs hold more than one hidden state.

Return type:

ModuleV3Outputs[TensorValue]