Skip to content

[refactor] Consolidate NVFP4 dequant logic into shared fp4_utils

8ce17ef
Select commit
Loading
Failed to load commit list.
Draft

[TRTLLM-12288][feat] Support NVFP4 W4A16 inference on Hopper for Nemotron H models #14009

[refactor] Consolidate NVFP4 dequant logic into shared fp4_utils
8ce17ef
Select commit
Loading
Failed to load commit list.