Open Models Almanac
Methodsinference & servinginference scheduling

single mention · inference & serving

Maximum-sequence tuning

Sets max-num-seqs to 32 as a context-fitting control.

The sources on this page only mention it in passing. The line above is the extraction's one-line gloss. See inference scheduling for the methods filed beside it.

Also called Max sequences tuning for context fitting, --max-num-seqs 32.

Filed under inference & serving › inference scheduling