Home · ASPLOS 2026 · Machine Learning Systems
ZipServ: Fast and Memory-Efficient LLM Inference with Hardware-Aware Lossless Compression
Ruibo Fan, Xiangrui Yu, Xinglin Pan, Zeyu Li, Weile Luo, Qiang Wang and 2 others
- Conference
- ASPLOS 2026
- Published
- 2026
- Pages
- 2264-2280
- Citations
- 0
The authors' abstract
This is the paper's own summary, in the paper's own words. It is dense on purpose — abstracts are written to compress.
No abstract is available for this paper from OpenAlex. Follow the DOI link above to read it at the publisher.
The plain-English explainer is not written yet
When it is, it will replace the abstract above and walk through six questions in order: what problem the paper attacks, what people did before, why that was not good enough, what the paper's idea is, why that idea works, and what the measurements actually showed. Terms get defined the first time they appear.
Related papers on Machine Learning Systems
- PyTorch 2: Faster Machine Learning Through Dynamic Python Bytecode Transformation and Graph Compilation 2024
- INFless: a native serverless system for low-latency, high-throughput inference 2022
- DOTA: detect and omit weak attentions for scalable transformer acceleration 2022
- AttAcc! Unleashing the Power of PIM for Batched Transformer-based Generative Model Inference 2024
- NeuPIMs: NPU-PIM Heterogeneous Acceleration for Batched LLM Inferencing 2024