Open Models Almanac
Methodsinference & servinginference quantization

single mention · inference & serving

FP8 W8A8 quantization with dynamic activation scaling

FP8 weight-and-activation quantization using amax-based dynamic activation scaling that does not require calibration.

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

Filed under inference & serving › inference quantization