Open Models Almanac
Methodsinference & servingreasoning control

general family · filed under inference & serving

Parallel test-time compute scaling

Test-time compute is increased by running inference trajectories or agents in parallel.

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

Also called in parallel.

sources
2
models
3
labs adopt it
0
strongest
evaluated

Documented in

Evidence

2 quotes from 2 sources, one card per model, each opening with its strongest.

How sources treat it
evaluated 2

DeepSeek-V3.2

DeepSeekdiscussed1 source

test-time compute can be scaled either serially through context management or in parallel

evaluatedinference servingin DeepSeek-V3.2DeepSeek
↑