SplitZip is a new GPU-friendly lossless compressor for KV cache tensors that exploits exponent redundancy to achieve over 600 GB/s compression throughput and up to 1.32x faster transfers in disaggregated LLM serving.
Zipserv: Fast and memory-efficient llm inference with hardware-aware lossless compression
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 2
citation-polarity summary
fields
cs.DC 2years
2026 2verdicts
UNVERDICTED 2roles
background 2polarities
background 2representative citing papers
UCCL-Zip adds lossless compression to GPU communication to reduce LLM bottlenecks while preserving exact numerical correctness.
citing papers explorer
-
SplitZip: Ultra Fast Lossless KV Compression for Disaggregated LLM Serving
SplitZip is a new GPU-friendly lossless compressor for KV cache tensors that exploits exponent redundancy to achieve over 600 GB/s compression throughput and up to 1.32x faster transfers in disaggregated LLM serving.
-
UCCL-Zip: Lossless Compression Supercharged GPU Communication
UCCL-Zip adds lossless compression to GPU communication to reduce LLM bottlenecks while preserving exact numerical correctness.