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

build_eos_tracker_for_request

build_eos_tracker_for_request()

async max.pipelines.lib.build_eos_tracker_for_request(default_eos_token_ids, request, encode_fn)

source

Builds an EOSTracker from request sampling params.

Parameters:

• default_eos_token_ids (set[int]) – Default EOS token IDs from tokenizer/model config.
• request (TextGenerationRequest) – Generation request; uses request.sampling_params for stops.
• encode_fn (Callable[[str, bool], Awaitable[ndarray[tuple[Any, ...], dtype[integer[Any]]]]]) – Async encode callable (text, add_special_tokens) -> token ids.

Returns:

Configured EOSTracker for this request.

Return type:

EOSTracker

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