MAX v25.1.1
Fix performance issues in autoregressive models with paged attention
by setting sensible default values for --max-num-steps that are
platform-specific.
IMPORTANT: To view this page as Markdown, append `.md` to the URL (e.g. /max/get-started.md). For the complete documentation index, see llms.txt.
Fix performance issues in autoregressive models with paged attention
by setting sensible default values for --max-num-steps that are
platform-specific.