1 citations · 1 across the 12 of their papers we have counts for
14 papers
Beyond Parallel Blindness: Information Floors and Model Gaps in Block Drafting
Xinwei Qiang, Xiang Fang, Chang Chen +3
Block drafters propose several tokens in one forward pass, before earlier target tokens are realised. Their rejection mixes two losses: missing within-block path information and im…
SmoothAgent: Efficient Long-Horizon LLM-Based Agent Serving with Lookahead Context Engineering
Zaifeng Pan, Qianxu Wang, Zhengding Hu +5
LLM-based agents execute multi-turn workflows with continuously growing contexts, where LLM calls are interleaved with tool invocations and environment feedback. To maintain model…
FlashCP: Load-Balanced Communication-Efficient Context Parallelism for LLM Training
Zheng Wang, Eric Liu, Linan Jiang +5
Context parallelism (CP) is essential for training large-scale, long-context language models, as it partitions sequences to reduce memory overhead. However, existing CP methods suf…
TLX: Hardware-Native, Evolvable MIMW GPU Compiler for Large-scale Production Environments
Yue Guan, Hongtao Yu, Peng Chen +10
Modern GPUs increasingly rely on specialized hardware units and asynchronous coordination mechanisms, so performance depends on orchestrating data movement, tensor-core computation…
FlashEvolve: Accelerating Agent Self-Evolution with Asynchronous Stage Orchestration
Zhengding Hu, Mingge Lu, Zhen Wang +8
LLM-based evolution has emerged as a promising way to improve agents by refining non-parametric artifacts, but its wall-clock cost remains a major bottleneck. We identify that this…
JigsawRL: Assembling RL Pipelines for Efficient LLM Post-Training
Zhengding Hu, Hehua Ouyang, Chang Chen +6
We present JigsawRL, a cost-efficient framework that explores Pipeline Multiplexing as a new dimension of RL parallelism. JigsawRL decomposes each pipeline into a Sub-Stage Graph t…
Pancake: Hierarchical Memory System for Multi-Agent LLM Serving
Zhengding Hu, Zaifeng Pan, Prabhleen Kaur +6
In this work, we identify and address the core challenges of agentic memory management in LLM serving, where large-scale storage, frequent updates, and multiple coexisting agents j…
ScaleSim: Serving Large-Scale Multi-Agent Simulation with Invocation Distance-Based Memory Management
Zaifeng Pan, Yipeng Shen, Zhengding Hu +6
LLM-based multi-agent simulations are increasingly adopted across application domains, but remain difficult to scale due to GPU memory pressure. Each agent maintains private GPU-re…
Syncopate: Efficient Multi-GPU AI Kernels via Automatic Chunk-Centric Compute-Communication Overlap
Xinwei Qiang, Yue Guan, Zhengding Hu +3
Communication has become a first-order bottleneck in large-scale GPU workloads, and existing distributed compilers address it mainly by overlapping whole compute and communication…
Patterns behind Chaos: Forecasting Data Movement for Efficient Large-Scale MoE LLM Inference
Zhongkai Yu, Yue Guan, Zihao Yu +6
Large-scale Mixture of Experts (MoE) Large Language Models (LLMs) have recently become the frontier open-weight models, achieving remarkable model capability similar to proprietary…
Amoeba: Runtime Tensor Parallel Transformation for LLM Inference Services
Haoyu Chen, Xue Li, Kun Qian +3
In Large Language Model (LLM) inference services, it is challenging to make a parallelism strategy configuration, to efficiently process the requests of variance context lengths. R…
KVFlow: Efficient Prefix Caching for Accelerating LLM-Based Multi-Agent Workflows
Zaifeng Pan, Ajjkumar Patel, Zhengding Hu +6
Large language model (LLM) based agentic workflows have become a popular paradigm for coordinating multiple specialized agents to solve complex tasks. To improve serving efficiency…
KPerfIR: Towards an Open and Compiler-centric Ecosystem for GPU Kernel Performance Tooling on Modern AI Workloads
Yue Guan, Yuanwei Fang, Keren Zhou +5
In this work, we propose KPerfIR, a novel multilevel compiler-centric infrastructure to enable the development of customizable, extendable, and portable profiling tools tailored fo…
WLB-LLM: Workload-Balanced 4D Parallelism for Large Language Model Training
Zheng Wang, Anna Cai, Xinfeng Xie +9
In this work, we present WLB-LLM, a workLoad-balanced 4D parallelism for large language model training. We first thoroughly analyze the workload imbalance issue in LLM training and…