π“Ÿ host1.bitchan.one

𓀐 @oBo9ip9S

⏱ 4d seenβ›“ 0πŸ‘ 0β§– 1

filter [-]

languages:onother

Wonder how hard it would be to implement. IIRC, llama.cpp merged some PRs a couple months ago that made some changes to how kv cache is stored and computed that seems to me would make implementing this pretty trivial. Maybe, dunno.⏱ 4d↩