2 citations · 2 across the 2 of their papers we have counts for
5 papers
Grouper: Scheduling Groups for Multi-Tenant Microsecond-Scale Microservices
Koosha Kazemi, Mohammad Siavashi, Ahmad Siavashi +1
Microsecond-scale core allocation makes colocating latency-critical services with batch work worthwhile. A thread that finds no work parks within microseconds and its core goes to…
Dissecting GPU Utilization for LLM Inference on Nvidia Hopper
Mohammad Siavashi, Gerald Q. Maguire, Dejan Kostic +1
A single SM utilization percentage can make an LLM inference workload look compute-saturated while hiding how much useful work is being done. The problem is not that the counter is…
Blink: CPU-Free LLM Inference by Delegating the Serving Stack to GPU and SmartNIC
Mohammad Siavashi, Mariano Scazzariello, Gerald Q. Maguire +2
Large Language Model (LLM) inference is rapidly becoming a core datacenter service, yet current serving stacks keep the host CPU on the critical path for orchestration and token-le…
Priority-Aware Preemptive Scheduling for Mixed-Priority Workloads in MoE Inference
Mohammad Siavashi, Faezeh Keshmiri Dindarloo, Dejan Kostic +1
Large Language Models have revolutionized natural language processing, yet serving them efficiently in data centers remains challenging due to mixed workloads comprising latency-se…
Phoenix -- A Novel Technique for Performance-Aware Orchestration of Thread and Page Table Placement in NUMA Systems
Mohammad Siavashi, Alireza Sanaee, Mohsen Sharifi +1
The emergence of symmetric multi-processing (SMP) systems with non-uniform memory access (NUMA) has prompted extensive research on process and data placement to mitigate the perfor…