LaProx reformulates KV cache eviction as an output-aware matrix approximation, enabling a unified global token selection strategy that preserves LLM performance at 5% cache size across long-context benchmarks.
Alisa: Accelerating large language model inference via sparsity-aware kv caching
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CL 1years
2026 1verdicts
UNVERDICTED 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
Reformulating KV Cache Eviction Problem for Long-Context LLM Inference
LaProx reformulates KV cache eviction as an output-aware matrix approximation, enabling a unified global token selection strategy that preserves LLM performance at 5% cache size across long-context benchmarks.