11 papers
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-…
ParEVO: Synthesizing Code for Irregular Data: High-Performance Parallelism through Agentic Evolution
Liu Yang, Zeyu Nie, Andrew Liu +4
The transition from sequential to parallel computing is essential for modern high-performance applications but is hindered by the steep learning curve of concurrent programming. Th…
Adapting AlphaEvolve to Optimize Fully Homomorphic Encryption on TPUs
Shruthi Gorantala, Jianming Tong, Asra Ali +7
The deployment of Fully Homomorphic Encryption (FHE) at scale is hindered due to its heavy computational overhead. While specialized hardware accelerators like Google Tensor Proces…
MIST: A Co-Design Framework for Heterogeneous, Multi-Stage LLM Inference
Abhimanyu Rajeshkumar Bambhaniya, Hanjiang Wu, Suvinay Subramanian +8
Modern LLM serving now spans multi-stage pipelines including RAG retrieval and KV cache reuse, each with distinct compute, memory, and latency demands. Inference engines expose a l…
Magellan: Autonomous Discovery of Novel Compiler Optimization Heuristics with AlphaEvolve
Hongzheng Chen, Alexander Novikov, Ngân Vũ +5
Modern compilers rely on hand-crafted heuristics to guide optimization passes. These human-designed rules often struggle to adapt to the complexity of modern software and hardware…
Concorde: Fast and Accurate CPU Performance Modeling with Compositional Analytical-ML Fusion
Arash Nasr-Esfahany, Mohammad Alizadeh, Victor Lee +9
Cycle-level simulators such as gem5 are widely used in microarchitecture design, but they are prohibitively slow for large-scale design space explorations. We present Concorde, a n…