10 papers
OctoPipe: Reducing Pipeline Bubbles for Heterogeneous Models via Co-Optimizing Partitioning, Placement, and Scheduling
Jihu Guo, Tenghui Ma, Wei Gao +6
Pipeline parallelism is widely used to train large language models (LLMs). However, increasing heterogeneity in model architectures exacerbates pipeline bubbles, thereby reducing t…
SAC: Disaggregated KV Cache System for Sparse Attention LLMs with CXL
Ruiyang Ma, Teng Ma, Junru Li +7
The scaling of LLMs toward long-context inference has shifted the primary serving system bottleneck from computation to memory capacity. Traditional solutions for dense attention m…
SpecGen: Accelerating Agentic Kernel Optimization with Speculative Generation
Jihu Guo, Sitian Lu, Tenghui Ma +4
Agentic kernel optimization automates manual GPU kernel tuning via iterative generation, validation, and profiling with reasoning LLMs, casting the optimization task as feedback-gu…
DisagFusion: Asynchronous Pipeline Parallelism and Elastic Scheduling for Disaggregated Diffusion Serving
Hantian Zha, Teng Ma, Yang Yong +7
Diffusion-based generation is increasingly powering production content pipelines; however, deploying these models at scale remains a significant challenge. Model weights frequently…
ROSE: Rollout On Serving GPUs via Cooperative Elasticity for Agentic RL
Wei Gao, Yuheng Zhao, Dilxat Muhtar +13
Agentic reinforcement learning (RL) is reshaping LLM post-training, but end-to-end training time is dominated by compute-intensive, multi-turn rollouts whose resource demand varies…
TokenCake: A KV-Cache-centric Serving Framework for LLM-based Multi-Agent Applications
Zhuohang Bian, Feiyang Wu, Zhuoran Li +2
Large Language Models (LLMs) are increasingly deployed in complex multi-agent applications that rely on external function calls. This workload creates severe performance challenges…