Open Models Almanac
Methodsinference & servinginference kernel

single mention · inference & serving

Operator fusion using torch.compile

Uses torch.compile to fuse operators and reduce kernel-launch overhead.

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 operator fusion (via torch.compile).

Filed under inference & serving › inference kernel