11 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…
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…
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…
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…
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…