Open Models Almanac
Methodsinference & servinginference kernel

implementation detail · filed under inference & serving

CUDA graph capture size reduction

Reducing the configured maximum CUDA graph capture size to address a CUDA graph or Mamba cache size error.

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

Also called reduce --max-cudagraph-capture-size.

sources
2
model
1
lab adopt it
1
strongest
used
↑