Quantize lm_head + embedding for Nemotron-H, add NVFP4 W4A16 recipe#1327
Open
ajrasane wants to merge 1 commit into
Open
Quantize lm_head + embedding for Nemotron-H, add NVFP4 W4A16 recipe#1327ajrasane wants to merge 1 commit into
ajrasane wants to merge 1 commit into