CELLServe formalizes SLO-constrained joint resource provisioning as an optimization problem with a dedicated algorithm, and introduces an opportunistic instance merging strategy for decode phase functions to reclaim fragmented resources.
Festina is presented, a profiling-guided, power-aware control plane to minimize cluster-wide energy for serverless LLM serving and performs energy-aware workload consolidation to reduce GPUs'static power consumption via SLO-aware migration.
Frontier open-weight models are increasingly available, but serving them still largely assumes datacenter infrastructure. We present FreeToken, an edge-native MoE serving system that treats a personal machine not as a small GPU, but as a unified, elastic inference platform. FreeToken co-designs the full serving stack, including model layout and loading, expert residency, CPU--GPU execution, agentic state reuse, and runtime memory management, around two realities of local AI: agent workloads continuously change their execution pattern, and edge hardware exposes heterogeneous resources whose balance differs from machine to machine. Rather than committing to a fixed offloading strategy, FreeToken continuously maps computation and model state onto the resources actually available. FreeToken supports more than 20 MoE models and real coding and tool-using agents across hardware ranging from an 8GB laptop GPU to a single workstation GPU. More importantly, it changes what these machines can practically serve, from a 35B model on a laptop to a 284B model on a gaming desktop and the 753B GLM-5.2 on a single workstation GPU. FreeToken turns open weights into deployable local software, making the machines users already own a practical platform for frontier-scale intelligence. We release the system at flashml.ai.
A ReRAM near-memory architecture that keeps expert weights resident behind high-bandwidth local reads and recovers occupancy with bounded core-local multicast pooling, coactivation-aware placement, and load-aware fetch, and sizes each communication level from induced demand is presented.
Roomie is presented, a model serving orchestration architecture that predicts and avoids kernel-level interference between colocated DNNs, and reduces SLO violations by up to 3x, while maintaining comparable, and in many cases superior, goodput relative to existing approaches.
This paper employs five lightweight machine learning models to predict query-specific latency, accuracy, resource usage, and response size for each model-size-quantization-device combination, and design a lightweight heuristic that approximates the BILP solution.