cache-compression

TaskPress introduces a query-agnostic KV cache compression framework that uses a task guide as a meta-query and quantization scale factors to prune irrelevant tokens, enabling reusable caches across diverse queries with negligible overhead.

KVpop introduces a learned KV cache eviction policy supervised by future-attention targets, achieving high compression rates (e.g., 98% performance at 75% compression) on Qwen3 models while maintaining quality.