3 papers
cs.DC2026
FlexNPU: Transparent NPU Virtualization for Dynamic LLM Prefill-Decode Co-location
Jiongjiong Gu, Jianfeng Wang, Zidong Han +19
Modern AI serving increasingly relies on NPUs for conventional inference and large language model serving. However, current NPU deployments commonly expose physical devices directl…
cs.AI2026
DIVE: Scaling Diversity in Agentic Task Synthesis for Generalizable Tool Use
Aili Chen, Chi Zhang, Junteng Liu +11
Recent work synthesizes agentic tasks for post-training tool-using LLMs, yet robust generalization under shifts in tasks and toolsets remains an open challenge. We trace this britt…
cs.PL2026
Beyond Pass-by-Pass Optimization: Intent-Driven IR Optimization with Large Language Models
Lei Qiu, Zi Yang, Fang Lyu +3
Modern compilers optimize programs through a sequence of modular passes over intermediate representations (IR). While this pass-by-pass paradigm offers engineering benefits, it suf…