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 module

max.pipelines.speculative.driver

Model-agnostic driver for sequential (eagle / MTP) speculative decoding.

Every sequential unified spec-decode module in the tree runs the same seven phases – merge, verify, mask, accept, shift, propose, pack – and differs only in how it calls its target, how it calls its draft, and what per-step cache bookkeeping the draft needs. SequentialDriver owns the phases; a model contributes a SpecDecodeTarget and a SequentialProposer.

The two adapters are deliberately not Module subclasses. The driver registers the target and draft modules under the same attribute names the hand-written modules used, so weight loading, state_dict keys and the weights registry are unchanged.

Sequential driver

DecodeKVSwap	A single per-step edit to the draft's PagedCacheValues.
DraftStepInput	Loop-carried state between draft steps.
Proposed	One draft invocation's contribution.
SequentialBatch	One spec-decode iteration's graph inputs, merged and broadcast.
SequentialDriver	Drives the sequential speculative-decoding loop.
SequentialProposer	A draft that emits one token per step, K steps deep.