Papers › FastKV: KV Cache Compression for Fast Long-Context Processing with Token-Selective Propagation

FastKV: KV Cache Compression for Fast Long-Context Processing with Token-Selective Propagation

3 Feb 2025arXiv:2502.01068archive 2025-07-28

Dongwon Jo, Jiwon Song, Yulhwa Kim, Jae-Joon Kim

While large language models (LLMs) excel at handling long-context sequences, they require substantial key-value (KV) caches to store contextual information, which can heavily burden computational efficiency and memory usage. Previous efforts to compress these KV caches primarily focused on reducing memory demands but were limited in enhancing latency. To address this issue, we introduce FastKV, a KV cache compression method designed to reduce latency for long-context inference. FastKV improves processing speed while preserving accuracy by adopting Token-Selective Propagation (TSP). This approach preserves full-context information in early layers of LLMs and selectively propagates only a portion of this information in later layers. This design enables FastKV to minimize redundant computation without sacrificing contextual fidelity. Our experimental results show that FastKV achieves up to 1.97× and 4.82× improvements in time-to-first-token (TTFT) and throughput, respectively, compared to baseline without KV cache compression. Moreover, FastKV successfully maintains accuracy within 1\% of the baseline on long-context benchmarks. Our code is available at https://github.com/dongwonjo/FastKV.

PaperPDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

dongwonjo/fastkv officialmentioned in papermentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Computational Efficiency

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

AttentionDense ConnectionsFeedforward NetworkGrouped-query attentionSPEEDSoftmax

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections