Rendered at 19:41:53 GMT+0000 (Coordinated Universal Time) with Cloudflare Workers.
arikrahman 16 hours ago [-]
I am very impressed with the KV Cache Compression work as well as the prefix cacheing making queries converge on practically free.
mmastrac 14 hours ago [-]
I've been working with an automatic incremental context compactor enabled and it's been surprisingly helpful. It was particularly effective with DS41f - I think I was running at an effective session length of 5M, with the model running around 300k-400k and it was holding on both speed and intelligence.
TBH I also ran the 400tok/s preview and that was just nuts. I just let the thing compact over and over over the course of a day attacking a couple of tough problems
nchmy 9 hours ago [-]
Can you share a link to thr automatic compactor? I've been noticing that when I get to around 60% context window, the cache will simply break and suddenly I've paid 50x more than expected. The only solution seems to be to compact or start a new session.
TBH I also ran the 400tok/s preview and that was just nuts. I just let the thing compact over and over over the course of a day attacking a couple of tough problems