Recently updated channels

Pick one to see only that channelBrowse all channels →
Matthew Bermantoday +20AI Engineertoday +9The Builderstoday +1Theo - t3․ggyesterday +115Sequoia Capitalyesterday +1a16zyesterday +1Reid Hoffmanyesterday +1Chris Williamsonyesterday +1Conversations with TyleryesterdayCitadel Securities2 days ago +1

Results

1 articles
Sort
ChannelMatthew BermanTopicKV caching & prefix reuseSpeakersSolo
Slides0:22EN
Matthew Berman· Oct 18, 2026DeepSeek's Memory Use: A Short Claim About KV CacheMatthew Berman · Forward FutureMatthew Berman links lower cache memory use to serving more tokens, but the excerpt does not state the comparison behind its figures.KV caching & prefix reuseInferenceInfrastructure & deployment