5 papers
ThunderAgent: A Simple, Fast and Program-Aware Agentic Inference System
Hao Kang, Ziyang Li, Weili Xu +7
Large language models(LLMs) are now used to power complex multi-turn agentic workflows. Existing systems run agentic inference by loosely assembling isolated components: an LLM inf…
OckBench: Measuring the Efficiency of LLM Reasoning
Zheng Du, Hao Kang, Song Han +2
Large language models (LLMs) such as GPT-5 and Gemini 3 have pushed the frontier of automated reasoning and code generation. Yet current benchmarks emphasize accuracy and output qu…
Slm-mux: Orchestrating small language models for reasoning
Chenyu Wang, Zishen Wan, Hao Kang +5
With the rapid development of language models, the number of small language models (SLMs) has grown significantly. Although they do not achieve state-of-the-art accuracy, they are…
Win Fast or Lose Slow: Balancing Speed and Accuracy in Latency-Sensitive Decisions of LLMs
Hao Kang, Qingru Zhang, Han Cai +4
Large language models (LLMs) have shown remarkable performance across diverse reasoning and generation tasks, and are increasingly deployed as agents in dynamic environments such a…
TurboAttention: Efficient Attention Approximation For High Throughputs LLMs
Hao Kang, Srikant Bharadwaj, James Hensman +3
Large language model (LLM) inference demands significant amount of computation and memory, especially in the key attention mechanism. While techniques, such as quantization and acc…