inference/research
verifiedhigh · 0.88updated 2026-10-03

CacheGen: KV Cache Compression and Streaming for Fast Large Language Model Serving (Zhang et al., UChicago/JCL)

paper

Fields

id
sources/qlab-cachegen-paper
URL
https://arxiv.org/abs/2310.07240
Publisher
arXiv
Kind
paper
Published
2023-10-11
Accessed
2026-10-03
notes
v6. Custom tensor encoder exploiting KV distributional properties; bandwidth-adaptive compression level.

Notes

v6. Custom tensor encoder exploiting KV distributional properties; bandwidth-adaptive compression level.

Cross-references

This record references no other records.