13 citations · 18 across the 12 of their papers we have counts for
12 papers
Coresets Before Score Sets: Evaluation-Unsupervised Prompt Subset Selection for LLM Benchmarks
Jihan Yao, Gantavya Bhatt, Arnav Das +16
We study LLM benchmark coreset selection: selecting a small subset of prompts over multiple benchmarks whose induced model scores and rankings approximate those obtained from the f…
TENT: A Declarative Slice Spraying Engine for Performant and Resilient Data Movement in Disaggregated LLM Serving
Feng Ren, Ruoyu Qin, Teng Ma +16
Modern GPU clusters rely on complex, heterogeneous interconnects. As large language model (LLM) serving shifts toward agentic reasoning, KVCache becomes a first-class mobile asset,…
SpecForge: A Flexible and Efficient Open-Source Training Framework for Speculative Decoding
Shenggui Li, Chao Wang, Yikai Zhu +14
Large language models incur high inference latency due to sequential autoregressive decoding. Speculative decoding alleviates this bottleneck by using a lightweight draft model to…
Not All Prefills Are Equal: PPD Disaggregation for Multi-turn LLM Serving
Zongze Li, Jingyu Liu, Zhen Xu +3
Prefill-Decode (PD) disaggregation has become the standard architecture for modern LLM inference engines, which alleviates the interference of two distinctive workloads. With the g…
When RL Meets Adaptive Speculative Training: A Unified Training-Serving System
Junxiong Wang, Fengxiang Bie, Jisen Li +14
Speculative decoding can significantly accelerate LLM serving, yet most deployments today disentangle speculator training from serving, treating speculator training as a standalone…
Understanding and Steering the Cognitive Behaviors of Reasoning Models at Test-Time
Zhenyu Zhang, Xiaoxia Wu, Zhongzhu Zhou +7
Large Language Models (LLMs) often rely on long chain-of-thought (CoT) reasoning to solve complex tasks. While effective, these trajectories are frequently inefficient, leading to…
FlashInfer-Bench: Building the Virtuous Cycle for AI-driven LLM Systems
Shanli Xing, Yiyan Zhai, Alexander Jiang +10
Recent advances show that large language models (LLMs) can act as autonomous agents capable of generating GPU kernels, but integrating these AI-generated kernels into real-world in…
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…
FlashInfer: Efficient and Customizable Attention Engine for LLM Inference Serving
Zihao Ye, Lequn Chen, Ruihang Lai +8
Transformers, driven by attention mechanisms, form the foundation of large language models (LLMs). As these models scale up, efficient GPU attention kernels become essential for hi…
QQQ: Quality Quattuor-Bit Quantization for Large Language Models
Ying Zhang, Peng Zhang, Mincong Huang +7
Quantization is a proven effective method for compressing large language models. Although popular techniques like W8A8 and W4A16 effectively maintain model performance, they often…
Mooncake: A KVCache-centric Disaggregated Architecture for LLM Serving
Ruoyu Qin, Zheming Li, Weiran He +4
Mooncake is the serving platform for Kimi, a leading LLM service provided by Moonshot AI. It features a KVCache-centric disaggregated architecture that separates the prefill and de…
Re-evaluating the Memory-balanced Pipeline Parallelism: BPipe
Mincong Huang, Chao Wang, Chi Ma +3
Pipeline parallelism is an essential technique in the training of large-scale Transformer models. However, it suffers from imbalanced memory consumption, leading to insufficient me…