Paper-Conference

KVSwap: Disk-aware KV Cache Offloading for Long-Context On-device Inference

From Threads to Tiles: T2T, a Compiler for CUDA-to-NPU Translation via 2D Vectorization

Leveraging Compilation Statistics for Compiler Phase Ordering

Accelerating Tensor-train Decomposition on Graph Neural Networks

Introducing Compiler Semantics into Large Language Models as Programming Language Translators: A Case Study of C to x86 Assembly

Optimizing Deep Learning Inference via Global Analysis and Tensor Expression

Combining Structured Static Code Information and Dynamic Symbolic Traces for Software Vulnerability Prediction

Optimizing Deep Learning Inference via Global Analysis and Tensor Expression

Optimizing Deep Learning Inference via Global Analysis and Tensor Expression

Characterizing DNN Models for Edge-Cloud Computing