Open Models Almanac
Methodsinference & servinginference quantization

single mention · inference & serving

TRT-LLM inference optimization to NVFP4 on Blackwell

An inference deployment optimization moving TRT-LLM serving to NVFP4 on Blackwell hardware.

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