4 papers
Schedule Repair for DAG Workflows under Link Disruptions
Mohammadali Khodabandehlou, Jared Coleman, Bhaskar Krishnamachari +1
Schedules for directed acyclic graph (DAG) workflows in networked IoT systems are typically computed assuming a static or generally stable network. In contested and adversarial env…
AKTS: Sub-Microsecond Kernel Policy Switching for Language-Model Agents
Mohammadali Khodabandehlou, Mahdi Alizadeh
GPU-backed LLM servers multiplex interactive requests with background batch work on the same CPUs; a fixed kernel policy serves one objective and loses the other, so agentic OS con…
Compression-Aware Abstention: Teaching LLMs to Refuse When KV-Compression Masks Remove Answer Evidence
Mohammadali Khodabandehlou, Bhaskar Krishnamachari
KV-cache compression reduces LLM inference memory by evicting context tokens, but when the evicted tokens contain answer-bearing evidence, the model may hallucinate instead of reco…
Studying the Effect of Schedule Preemption on Dynamic Task Graph Scheduling
Mohammadali Khodabandehlou, Jared Coleman, Niranjan Suri +1
Dynamic scheduling of task graphs is often addressed without revisiting prior task allocations, with a primary focus on minimizing makespan. We study controlled schedule preemption…