[samuelknight]

It has some weird side effects though. for example KV-caches are implemented in fixed incremental token blocks (1024 from the providers I used) instead of simply caching up to the most recent input prompt input. It results in up to 1023 additional input (cache miss) tokens per inference.

[wren6991]

Sounds a lot like running the Qwen3.5/3.6-series models at home: you need checkpoints for the recurrent state (GDN in the case of Qwen). You avoid the miss for the common case of 100% prefix match (e.g. during interleaved tool calls and thinking) by keeping an additional checkpoint for the actual last generated token. If you're a cloud provider serving many concurrent clients then you might prefer to skip that complexity and always take the 1k worst-case prefill hit.

SWA has a similar issue. Unless you keep the entire KV prefix lying around (which is not unreasonable: you retain flop + bandwidth benefits but lose capacity benefits), you need to start 1 window back from the rollback point, in order to refill the sliding window before going into normal prefill.