20 results for “cache compression”
CS papers onlyHybrid search: Keyword + semantic, ranked by combined score.ⓘ
Want pure semantic search? Try claim verification →
This paper presents ZipFusion, a method that enables attention to consume losslessly compressed key-value (KV) cache directly, improving model decode throughput and reducing memory-bandwidth bound.
Junjie Peng, You Wu, Haoyi Wu, Jialong Han +3 more
GRKV introduces a training-free KV-cache merging method that uses global regression to distribute information from evicted tokens, solving the over-merging problem inherent in span-based retention.
Moment-KV introduces a novel momentum-based technique to compress the Key-Value (KV) cache during the decoding phase of LLM generation, significantly improving fidelity in long-generation tasks.
This paper investigates the redundancy of the prompt KV cache during language model decoding, finding that the structure provided by chat templates is the primary source of redundancy, not the actual…
This paper introduces a provably sound runtime meter for KV-cache quantization to ensure compression does not damage the served request in real-time.
This paper analyzes the efficiency of AI coding agents and identifies the opportunity for reducing unnecessary turns in their loop engineering process.
This paper proposes C^2, a set of techniques to improve the spatial locality of succinct tries, resulting in faster query performance and reduced memory footprint.
André Ribeiro, Rúben Garrido, Violeta Ramos, António Alberto +27 more
This paper presents the 2026 Algorithmic Information Theory Data Compression Challenge, evaluating lossless compressors under realistic constraints and revealing performance dependencies.
The paper characterizes the memory-rate trade-off for demand-private coded caching with heterogeneous file sizes and cache capacities.
The authors extend the Block Decomposition Method (BDM) to utilize dependencies between blocks to reduce description length.
Shubham Tiwari, Tapan Chugh, Nash Rickert, Simon Peter +2 more
This paper presents a new KVCache management layer called CacheWise that improves performance for coding agent workloads.
Jieke Shi, Junda He, Wenjia Jiang, Weifeng Sun +10 more
Brevis compresses model checkpoints by synthesizing self-contained DSL programs that reconstruct tensors bit-exactly, reducing storage requirements and achieving high compression and decompression spe…
Shuheng Gao, Yuankai Fan, Jiaqiang Ma, Jiawei Shao +2 more
VisMemo is a serving system that enables approximate KV cache reuse for modern vision-language models to reduce prefill latency and memory overhead.
Ke-Han Lu, Keqi Deng, Ruchao Fan, Rui Zhao +1 more
The paper proposes SpeechKV, a method to compress speech sequences inside large language models using a learned pooling, maintaining performance and delivering decoding speedup.