3 papers
cs.LG2026
AcceptMoE: Commitment-Weighted Self-Sizing Verifier Expert Sets for Efficient MoE Speculative Decoding
Shuang Liang, Hao Mark Chen, Zhiwen Mo +4
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…
cs.DC2026
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…
cs.AR2026
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…