Mastering Long Contexts in LLMs with KVPress

Recent Developments in LLM Architectures: KV Sharing, mHC, and Compressed Attention

From Gemma 4 to DeepSeek V4, How New Open-Weight LLMs Are Reducing Long-Context Costs

Understanding and Coding the KV Cache in LLMs from Scratch

KV caches are one of the most critical techniques for efficient inference in LLMs in production.

KVMem: Virtualizing Million-Token Agent Workspaces on a Consumer GPU

KVMem is a KV-context virtualization system that allows large language model agents to maintain workspaces exceeding both GPU key‑value capacity and the model’s native context window. It stores overflowed history as paged KV state across GPU memory, host memory, and NVMe, using lightweight, model‑native attention‑space indexes to retrieve relevant historical blocks. Evaluations on long‑context agent benchmarks show that KVMem improves task utility and inference efficiency, enabling up to one million‑token workspaces on consumer GPUs and achieving interactive responsiveness in local deployments.

Judge Arena: Benchmarking LLMs as Evaluators

Still: Amortized KV Cache Compaction in a Single Forward Pass

arXiv:2606. 07878v1 Announce Type: new Abstract: The KV cache is the memory bottleneck of long-horizon language model deployment.

100-LongBench: Are de facto Long-Context Benchmarks Literally Evaluating Long-Context Ability?

arXiv:2505. 19293v2 Announce Type: replace-cross Abstract: Long-context capability is considered one of the most important abilities of LLMs, as a truly long context-capable LLM enables users to effortlessly process many originally exhausting tasks -- e.

A Universal Context-Reuse Layer for Cross-Model KV Sharing

arXiv:2608.30963v1 Announce Type: cross Abstract: Modern large language model (LLM) serving systems increasingly operate over repeated or shared context, yet each model typically performs its own pre...

Long Context Isn’t Free — I Built a Safe Prompt-Pruning Layer That Makes LLM Systems Work

LLMs don’t fail because they forget—they fail because they remember too much. As conversations grow, prompts accumulate redundant and low-value tokens, driving up cost and latency while silently degrading output quality.

CateKV: On Sequential Consistency for Long-Context LLM Inference Acceleration

arXiv:2608.30295v1 Announce Type: cross Abstract: Large language models (LLMs) have demonstrated strong capabilities in handling long-context tasks, but processing such long contexts remains challeng...

CompressKV: Semantic-Retrieval-Guided KV-Cache Compression for Resource-Efficient Long-Context LLM Inference

arXiv:2606. 24467v1 Announce Type: new Abstract: Long-context large language model (LLM) inference is increasingly constrained by the memory footprint and decoding cost of key-value (KV) caches, limiting sustainable deployment on resource-constrained hardware.

Dense Contexts Are Hard Contexts: Lexical Density Limits Effective Context in LLMs

arXiv:2606. 06203v1 Announce Type: cross Abstract: Input length and the position of relevant information are widely cited as the primary causes of degraded LLM long-context performance.

CompressKV: Semantic-Retrieval-Guided KV-Cache Compression for Resource-Efficient Long-Context LLM Inference

Long-context large language model (LLM) inference is increasingly constrained by the memory footprint and decoding cost of key-value (KV) caches, limiting sustainable deployment on resource-constrained hardware. Existing KV cache eviction methods typically apply heuristic token scoring over all heads in GQA-based LLMs.