Open Models Almanac
Methodsinference & servinginference kernel

single mention · inference & serving

HPC-Ops attention backend

The HPC-Ops attention backend enabled through the HPC_ATTN backend setting.

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 HPC_ATTN.

Filed under inference & serving › inference kernel