3 papers
cs.OS2026
AKTS: Sub-Microsecond Kernel Policy Switching for Language-Model Agents
Mohammadali Khodabandehlou, Mahdi Alizadeh
GPU-backed LLM servers often multiplex interactive requests with background batch work on the same CPUs. During a request burst, the scheduler should protect time-to-first-token; b…
cs.CL2026
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…
cs.DC2026
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…