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

token_sampler

token_sampler()

max.pipelines.sampling.token_sampler(sampling_config, device, return_logits=False, needs_bitmask_input=None)

source

Builds a sampling graph that samples tokens from logits.

Parameters:

• sampling_config (SamplingConfig) – Sampling configuration (top-k, temperature, etc.).
• device (DeviceRef) – Device for the graph inputs and ops.
• return_logits (bool) – Whether the graph should expose logits as an output.
• needs_bitmask_input (bool | None) – Whether to wire a bitmask input into the graph. When None, falls back to sampling_config.enable_structured_output. Callers should pass True explicitly when tool-call grammars can fire even though --enable-structured-output is off.

Returns:

A graph that takes logits (and optional penalty inputs) and outputs tokens.

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