arXiv Computation and Language
KVShareArena: KV-Cache Reuse Across Contexts and Model Checkpoints
Read the original on arXiv Computation and Language →The Flow has not summarised this story yet — read it at arXiv Computation and Language.
Related stories
arXiv AI
Jun 2
Leyline: KV Cache Directives for Agentic Inference
arXiv:2606. 01065v1 Announce Type: cross Abstract: Modern KV cache management assumes the chatbot workload: prompts arrive once and the cache grows append-only, so prefix caching and forward-only eviction are correct by construction.
arXiv Machine Learning
Aug 4
RestoreKV: Recovering Full-Cache Behavior Under Aggressive Query-Agnostic KV Cache Eviction
arXiv:2608. 01247v1 Announce Type: cross Abstract: Query-agnostic KV cache eviction compresses a context once and reuses the resulting cache for arbitrary future queries, but performance can collapse under tight budgets.
arXiv AI
Aug 18
Learning Agent Execution for KV-Cache Management in Agentic Serving
arXiv:2608. 14624v1 Announce Type: new Abstract: Multi-agent LLM systems have emerged as an important deployment paradigm for AI services, where each user request is decomposed into a sequence of specialized agents.
arXiv AI
Aug 11
KVDiagnosis: A Diagnostic Benchmark for KV-Cache Compression in Long-Context Language Models
arXiv:2608. 09412v1 Announce Type: new Abstract: KV-cache compression reduces long-context memory, but aggregate task scores reveal neither which correct executions fail nor why.
Hugging Face Trending Papers
Aug 2
RestoreKV: Recovering Full-Cache Behavior Under Aggressive Query-Agnostic KV Cache Eviction
Query-agnostic KV cache eviction compresses a context once and reuses the resulting cache for arbitrary future queries, but performance can collapse under tight budgets. Existing methods primarily improve which original KV pairs are retained.
arXiv Computation and Language
Sep 4
Random Attention: Rethinking KV Cache Eviction for Efficient Reasoning
The paper introduces Random Attention, a method that evicts KV cache entries uniformly at random within each attention head while preserving the prompt. Experiments on four models and six reasoning tasks show that this simple strategy matches the performance of the best existing eviction methods and achieves 32‑43% higher throughput in vLLM deployments. The authors explain that the prompt is the most fragile cache component and that reasoning traces are redundantly stored across text and attention heads, making a selection score unnecessary.