6 papers
When Does Disaggregation Pay? Simulating Prefill--Decode--Attention--FFN Specialization for Agentic LLM Inference
Przemyslaw Forys, Haoran Wu, Can Xiao +8
Agentic inference now dominates the LLM inference landscape, requiring LLMs to actively engage in multi-turn interactions with tool-calling capabilities. This introduces a more com…
MemExplorer: Navigating the Heterogeneous Memory Design Space for Agentic Inference NPUs
Haoran Wu, Zeyu Cao, Yao Lai +16
Emerging agentic large language model (LLM) workloads are driving rapidly growing demand for memory capacity and bandwidth. Different phases of inference, such as prefill and decod…
KernelCraft: Benchmarking for Agentic Close-to-Metal Kernel Generation on Emerging Hardware
Jiayi Nie, Haoran Wu, Yao Lai +9
New AI accelerators with novel instruction set architectures (ISAs) often require developers to manually craft low-level kernels, a time-consuming and error-prone process that does…
NPU Design for Diffusion Language Model Inference
Binglei Lou, Haoran Wu, Kevin Lau +9
Diffusion-based LLMs (dLLMs) fundamentally depart from traditional autoregressive (AR) LLM inference: they leverage bidirectional attention, block-wise KV cache refreshing, cross-s…
Group Policy Gradient
Junhua Chen, Zixi Zhang, Hantao Zhong +1
We introduce Group Policy Gradient (GPG), a family of critic-free policy-gradient estimators for general MDPs. Inspired by the success of GRPO's approach in Reinforcement Learning…
Combating the Memory Walls: Optimization Pathways for Long-Context Agentic LLM Inference
Haoran Wu, Can Xiao, Jiayi Nie +15
LLMs now form the backbone of AI agents across a diverse range of applications, including tool use, command-line interfaces, and web or computer interaction. These agentic LLM infe…