serve: speculative decode serves logprobs from each token's own row; verify rows strided by the head width (refs #1781) - #2267

serve: speculative decode serves logprobs from each token's own row; verify rows strided by the head width (refs #1781)#2267

bong-water-water-bong merged 6 commits into

main1bit-MONSTER/engine:mainfrom

cl-npuperf/1781-spec-logprobs1bit-MONSTER/engine:cl-npuperf/1781-spec-logprobsCopy head branch name to clipboard