2026
IndexMem: Learned KV-Cache Eviction with Latent Memory for Long-Context LLM Inference
ICML 2026poster
Large Language Models (LLMs) are increasingly expected to operate over long contexts, yet standard softmax attention incurs a KV cache that grows linearly with sequence length, quickly becoming the bottleneck for long context inference. A practical remedy is to evict less important KV entries; howev…