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 module

max.nn.graph_groups

Graph groups: the named inputs or outputs one model feature brings.

A graph’s output tree is a handful of groups, such as the logits or the hidden states a drafter reads. Each group draws its fields from a fixed set, whatever model it appears in, so the serving engine learns to read a group once, by its GraphGroup.kind, rather than once per model.

Graph groups

ConvStates	The short-convolution states a decoder writes back for the next step.
DecoderOutputs	A decoder graph's named outputs: its logits, any hidden_states, and any state it writes back.
GraphGroup	The named graph inputs or outputs of one feature, in graph order.
HiddenStates	Hidden states a decoder returns for a drafter, a capture, or the next pipeline stage, keyed by the one mode it ran in.
Logits	The decoder's logits: the next token's, and any others requested.
LogitsName	The outputs a Logits group can hold.
SparseIndices	The rows a sparse-attention indexer selected, for a drafter to reuse.