IMPORTANT: To view this page as Markdown, append `.md` to the URL (e.g. /get-started.md). For the complete documentation index, see llms.txt.

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 class

CacheLeafKind

`CacheLeafKind`

class max.nn.kv_cache.CacheLeafKind(value, names=<not given>, *values, module=None, qualname=None, type=None, start=1, boundary=None)

source

Bases: Enum

What a child of a cache tree holds.

ATTENTION = 'attention'

source

Keys and values a span of tokens wrote, read through an attention op.

RECURRENT = 'recurrent'

source

One fixed-size state carrying every token before it.