15 citations · 27 across the 31 of their papers we have counts for
10 papers · 1 filter
Koi: Evidence-Guided, Self-Calibrating Planning for Multi-Cloud, Heterogeneous LLM Inference Fleets
Mankeerat Sidhu, Gangmuk Lim, Hetarth Chopra +10
Deploying a large language model (LLM) requires choosing the right accelerator, parallelization strategy, engine configuration, and replica count amongst ~140 other variables acros…
FreeToken: Efficient Edge-Native MoE Serving with Bandwidth-Adaptive Execution
Shuo Yang, Xiaoze Fan, Melissa Pan +8
Frontier open-weight models are increasingly available, but serving them still largely assumes datacenter infrastructure. We present FreeToken, an edge-native MoE serving system th…
RLBoost: Harvesting Preemptible Resources for Cost-Efficient Reinforcement Learning on LLMs
Yongji Wu, Xueshen Liu, Haizhong Zheng +5
Reinforcement learning (RL) has become essential for unlocking advanced reasoning capabilities in large language models (LLMs). RL workflows involve interleaving rollout and traini…
Prism: Cost-Efficient Multi-LLM Serving via GPU Memory Ballooning
Shan Yu, Yifan Qiao, Mingyuan Ma +18
Inference providers must maintain availability for many LLMs, including low-volume but essential models, making resource efficiency increasingly important as token prices fall. Ana…
HeterMoE: Efficient Training of Mixture-of-Experts Models on Heterogeneous GPUs
Yongji Wu, Xueshen Liu, Shuowei Jin +6
The Mixture-of-Experts (MoE) architecture has become increasingly popular as a method to scale up large language models (LLMs). To save costs, heterogeneity-aware training solution…
SkyStore: Cost-Optimized Object Storage Across Regions and Clouds
Shu Liu, Xiangxi Mo, Moshik Hershcovitch +11
Modern applications span multiple clouds to reduce costs, avoid vendor lock-in, and leverage low-availability resources in another cloud. However, standard object stores operate wi…
Locality-aware Fair Scheduling in LLM Serving
Shiyi Cao, Yichuan Wang, Ziming Mao +10
Large language model (LLM) inference workload dominates a wide variety of modern AI applications, ranging from multi-turn conversation to document analysis. Balancing fairness and…
MoE-Lightning: High-Throughput MoE Inference on Memory-constrained GPUs
Shiyi Cao, Shu Liu, Tyler Griggs +6
Efficient deployment of large language models, particularly Mixture of Experts (MoE), on resource-constrained platforms presents significant challenges, especially in terms of comp…
NEO: Saving GPU Memory Crisis with CPU Offloading for Online LLM Inference
Xuanlin Jiang, Yang Zhou, Shiyi Cao +2
Online LLM inference powers many exciting applications such as intelligent chatbots and autonomous agents. Modern LLM inference engines widely rely on request batching to improve i…
ConServe: Fine-Grained GPU Harvesting for LLM Online and Offline Co-Serving
Yifan Qiao, Shu Anzai, Shan Yu +10
Large language model (LLM) serving demands low latency and high throughput, but high load variability makes it challenging to achieve high GPU utilization. In this paper, we identi…