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 module

max.pipelines.architectures.unified_dflash_gemma4_31b

Unified DFlash speculative decoding for Gemma4 31B.

The draft checkpoint (z-lab/gemma-4-31B-it-DFlash) is in the native DFlash format; its config parsing is shared with the Llama3 DFlash pipeline.