Re:Qwen3.6-35B-A3B: Agentic Coding Power, Now Open to All
by FuckButtons on Thursday April 16, 2026 @06:56PM
(#47800567)
if I understand you correctly, this is essentially what vllm does with their paged cache, if I’ve misunderstood I apologize.
[ Parent
| on HN ]
Re:Qwen3.6-35B-A3B: Agentic Coding Power, Now Open to All
by zozbot234 on Thursday April 16, 2026 @07:08PM
(#47800686)
Paged Attention is more of a low-level building block, aimed initially at avoiding duplication of shared KV-cache prefixes in large-batch inference. But you're right that it's quite related. The llama.cpp folks are still thinking about it, per a recent discussion from that project: https://github.com/ggml-org/llama.cpp/discussions/21961