3 papers
cs.DC2026
DynBranch: Speculative Subgraph Reuse for Dynamic Agentic LLM Serving
Junyi Shen, Noppanat Wadlom, Zhengyuan Su +1
Agentic LLM workflows decide their execution paths at runtime. Downstream computation may be predictable, or may have run before, yet it cannot begin until the model or the user re…
cs.LG2026
MXSens: Sensitivity-Aware Mixed-Precision Quantization for Efficient LLM Inference
Simla Burcu Harma, Danila Mishin, Zhengyuan Su +7
4-bit quantization enables efficient LLM inference, but suffers from significant accuracy degradation due to outliers. Prior work addresses this problem via data rotation or mixed-…
cs.LG2024
Syno: Structured Synthesis for Neural Operators
Yongqi Zhuo, Zhengyuan Su, Chenggang Zhao +1
The desires for better prediction accuracy and higher execution performance in neural networks never end. Neural architecture search (NAS) and tensor compilers are two popular tech…