11 papers
AcceptMoE: Commitment-Weighted Self-Sizing Verifier Expert Sets for Efficient MoE Speculative Decoding
Shuang Liang, Hao Mark Chen, Hao +6
Speculative decoding verifies a tree of draft tokens in one target-model forward pass. For a mixture-of-experts (MoE) target, however, parallel verification can activate the union…
TileSight: A First-Principles Tile-Centric Analytical GPU Performance Model from Cores to Clusters
Zhiwen Mo, Yu Cheng, Lei Wang +12
Recent GPU programming frameworks such as Triton, TileLang, and CUDA Tile adopt tiles as first-class primitives, making tile-centric programming the prevailing approach for high-pe…
DeepStack: Facilitating Co-Design Exploration of 3D DRAM-Stacked Accelerators for Distributed LLM Inference
Zhiwen Mo, Guoyu Li, Hao Mark Chen +11
Advances in hybrid bonding and packaging have driven growing interest in 3D DRAM-stacked AI accelerators. As large language models (LLMs) scale to hundreds of billions or trillions…
FastTTS: Accelerating Test-Time Scaling for Edge LLM Reasoning
Hao Mark Chen, Zhiwen Mo, Guanxi Lu +4
Recent advances in reasoning Large Language Models (LLMs) are driving the emergence of agentic AI systems. Edge deployment of LLM agents near end users is increasingly necessary to…
T-MAN: Enabling End-to-End Low-Bit LLM Inference on NPUs via Unified Table Lookup
Jianyu Wei, Qingtao Li, Shijie Cao +5
Large language models (LLMs) are increasingly deployed on customer devices. To support them, current devices are adopting SoCs (System on Chip) with NPUs (Neural Processing Unit) i…
LUT Tensor Core: A Software-Hardware Co-Design for LUT-Based Low-Bit LLM Inference
Zhiwen Mo, Lei Wang, Jianyu Wei +8
Large Language Model (LLM) inference becomes resource-intensive, prompting a shift toward low-bit model weights to reduce the memory footprint and improve efficiency. Such low-bit…