Presented by
90/30 Club
We meet weekly in-person to talk about new ML papers! Come and join the discussion!
Hosted By
27 Going
90/30 Club Reading: DeepSeek-V4.1-Flash: Pushing the Limits of KV Cache Compression
Registration
About Event
Come join us for a group discussion of "DeepSeek-V4.1-Flash: Pushing the Limits of KV Cache Compression"
Paper link: https://arxiv.org/abs/2609.19969
DeepSeek-V4.1-Flash targets the real cost bottleneck of long-horizon agents—input-heavy prefill and enormous KV caches—using asymmetric prefill/decode compute and aggressive cache compression to cut compute, memory, storage, and bandwidth costs while improving agentic performance.
Event Schedule:
7pm-8pm: Quiet reading time, grab a snack and read! (optional)
8pm-9pm: Group discussion about the paper 📝
9pm-10pm: We have our space for a bit longer, stay to socialize or network!
Our event is hosted within Mox SF, the gracious donors of the space where we will meet.
Presented by
90/30 Club
We meet weekly in-person to talk about new ML papers! Come and join the discussion!
Hosted By
27 Going