← Search

Ziyu Huang

2 accepted papers

2025

ClusterFusion: Expanding Operator Fusion Scope for LLM Inference via Cluster-Level Collective Primitive

NeurIPS 2025poster

Large language model (LLM) decoding suffers from high latency due to fragmented execution across operators and heavy reliance on off-chip memory for data exchange and reduction. This execution model limits opportunities for fusion and incurs significant memory traffic and kernel launch overhead. Wh…

Cited by 0Source ↗Scholar ↗
2025

Enhancing DETR Efficiency with Inter-Object Relationship and Semantic Spectral Decomposition-Based Distillation

ICASSP 2025accepted

DEtection TRansformer (DETR) is an innovative object detection framework based on transformer architecture that achieves end-to-end detection using a self-attention mechanism, moving away from traditional CNN-based approaches. However, the high computational cost of DETR models limits their deployme…

Cited by 0Source ↗Scholar ↗