Model techniques map
Techniquesinference & servinginference scheduling

implementation detail · filed under inference & serving

Max sequences tuning

A configuration detail that sets the maximum number of sequences to fit a target context length.

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

source
1
model
1
lab adopt it
1
strongest
used

How sources treat it

One count per evidence span, weakest treatment to strongest.

used 1

Documented in

Evidence

1 span quoted from the sources, strongest treatment first.

--max-num-seqs 32 — the single knob for fitting 1M context

usedinference servingin GLM-5.3vLLM

Filed alongside

Other methods under inference & serving :: inference scheduling.