qwen4_exp: serve the block-FP8 dense projections natively (+25% decode) - #392
Open
gberasmus87 wants to merge 3 commits into
Open
qwen4_exp: serve the block-FP8 dense projections natively (+25% decode)#392gberasmus87 wants to merge 3 commits into
gberasmus87 wants to merge 3 commits into
