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 class

EOSTracker

`EOSTracker`

class max.pipelines.context.EOSTracker(*, eos_token_ids=<factory>, eos_sequences=<factory>, eos_stop_strings=<factory>)

source

Bases: BaseModel

Centralized EOS tracking: single-ID, sequence-ID, and stop-sequence checks.

Used by Context and sampling to decide when generation stops and which token IDs to mask during min_tokens. Built once (e.g. by tokenizer from request params) and passed into context, so eos fields are immutable; Server and Context both use this type.

Three kinds of checks:

EOS Single ID: token in eos_token_ids
EOS Sequence ID: suffix of generated_tokens matches any eos_sequences
EOS String Stop Sequence: decoded text contains a stop string.

Parameters:

eos_token_ids (set[int])
eos_sequences (Sequence[Sequence[int]])
eos_stop_strings (Sequence[str])

`eos_sequences`

eos_sequences: Sequence[Sequence[int]]

source

`eos_stop_strings`

eos_stop_strings: Sequence[str]

source

`eos_token_ids`

eos_token_ids: set[int]

source

`is_eos_from_string()`

is_eos_from_string(next_token_decoded)

source

If a stop sequence is detected, return the matched sequence. Else, return None.

Parameters:: next_token_decoded (str)
Return type:: str | None

`is_eos_from_tokens()`

is_eos_from_tokens(generated_tokens)

source

Checks for end-of-sequence conditions.

This function performs two checks:

Whether the newly generated token is in the set of eos_token_ids.
Whether appending the new token results in a sequence that matches any per-request stop sequence. Note: If called with a span of multiple newly generated tokens, EOS occurring before the final token in that span may not be detected by this method.

Parameters:: generated_tokens (ndarray[tuple[Any, ...], dtype[int64]])
Return type:: bool

`model_config`

model_config: ClassVar[ConfigDict] = {}

source

Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

`model_post_init()`

model_post_init(_EOSTracker__context)

source

Post-initialization hook to set the maximum stop length and continuation tail.

Parameters:: _EOSTracker__context (Any)
Return type:: None

EOSTracker​

eos_sequences​

eos_stop_strings​

eos_token_ids​

is_eos_from_string()​

is_eos_from_tokens()​

model_config​

model_post_init()​