The Kwon Paper's Attention Name
ArchiveEasy
Kwon et al. (2023) introduced a KV-cache memory management scheme inspired by OS virtual memory paging — the core optimization behind vLLM. Name it (one word, hyphens accepted). Flag format: CONGRESS{name}. Example: CONGRESS{slabattention}.
Show hint
OS term + attention.
Archive — no submissions accepted
This challenge is preserved for reference. Play live challenges at /challenges.