For the complete documentation index, see llms.txt. Markdown versions of all pages are available by appending .md to any URL (e.g. /max/get-started.md).

Python function

ragged_token_merger

ragged_token_merger()

max.pipelines.speculative.ragged_token_merger(device)

source

Builds a graph that merges prompt and draft tokens into a single ragged sequence.

Parameters:

device (DeviceRef) – Device for the graph inputs and merge op.

Returns:

A graph that takes prompt tokens, prompt row offsets, and draft tokens and outputs merged tokens and merged row offsets.

Return type:

Graph

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