Presented by
90/30 Club
We meet weekly in-person to talk about new ML papers! Come and join the discussion!
Hosted By
100 Went
Featured in
San Francisco
90/30 Club Reading: DeepSeek-V4.1-Flash: Pushing the Limits of KV Cache Compression
Registration
Past Event
Please click on the button below to join the waitlist. You will be notified if additional spots become available.
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
100 Went