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.cross_attention
The sequential proposers of a draft that keeps no cache of its own.
Gemma 4’s assistant has no K or V projections: each of its layers attends
with its queries alone into the target’s own sliding-window or
full-attention cache, so the driver hands it the target’s leaves. A ModuleV3
assistant runs through CrossAttentionModuleV3MTPProposer.
Drafts
CrossAttentionDraft | The draft-side surface CrossAttentionMTPProposer drives. |
|---|---|
CrossAttentionModuleV3Draft | The ModuleV3 draft CrossAttentionModuleV3MTPProposer drives. |
Proposers
CrossAttentionMTPProposer | Drafts one token a step, attending into the target's caches. |
|---|---|
CrossAttentionModuleV3MTPProposer | Drafts one token a step on ModuleV3, attending into the target's caches. |