11 papers
Deltoris: Enabling Real-time VLA Inference in Embodied AI via Bit-level Sparsity and Speculative Inference
Zheng Liu, Zeyu Guo, Zihan Liu +9
Vision-language-action (VLA) models have emerged as a key component in embodied AI. Among existing approaches, diffusion-based VLA models achieve superior motion quality and genera…
GF-DiT: Scheduling Parallelism for Diffusion Transformer Serving
Xinwei Qiang, Yifan Hu, Shixuan Sun +6
Diffusion Transformers (DiTs) have become the dominant architecture for image and video generation, creating growing demand for efficient DiT serving. Existing systems assign each…
Arena: Efficiently Training Large Models via Dynamic Scheduling and Adaptive Parallelism Co-Design
Chunyu Xue, Weihao Cui, Quan Chen +10
Efficiently training large-scale models (LMs) in GPU clusters involves two separate avenues: inter-job dynamic scheduling and intra-job adaptive parallelism (AP). However, existing…
Justitia: Fair and Efficient Scheduling of Task-parallel LLM Agents with Selective Pampering
Mingyan Yang, Guanjie Wang, Manqi Luo +6
LLM agents, which often comprise parallel inference tasks, are commonly adopted to solve real-world problems. When serving such task-parallel LLM agents in shared GPU servers, the…
Constraint-Aware Generative Re-ranking for Multi-Objective Optimization in Advertising Feeds
Chenfei Li, Hantao Zhao, Weixi Yao +4
Optimizing reranking in advertising feeds is a constrained combinatorial problem, requiring simultaneous maximization of platform revenue and preservation of user experience. Recen…
Flare: Anomaly Diagnostics for Divergent LLM Training in GPU Clusters of Thousand-Plus Scale
Weihao Cui, Ji Zhang, Han Zhao +5
The rapid proliferation of large language models has driven the need for efficient GPU training clusters. However, it is challenging due to the frequent occurrence of training anom…