PKU SEC Lab Claim this profile

[DAC'25] Official implement of "HybriMoE: Hybrid CPU-GPU Scheduling and Cache Management for Efficient MoE Inference"

This repo summarizes papers for efficient PPML across protocol, model, and system levels.

Code release for AdapMoE accepted by ICCAD 2024

Dysl-vla：Official code for "DySL-VLA: Efficient Vision-Language-Action Model Inference via Dynamic-Static Layer-Skipping for Robot Manipulation". A framework that dynamically skips VLA layers based on action importance, achieving 3.75× speedup and 85.7× training reduction on robotic manipulation tasks.

Code release for LightMamba accepted by DATE 2025

Implementation of "Orchestrating Dual-Boundaries: An Arithmetic Intensity Inspired Acceleration Framework for Diffusion Language Models"

No description.

Code release for MPCViT accepted by ICCV 2023

No description.

No description.

KEEP：Official code for "KEEP: A KV-Cache-Centric Memory Management System for Efficient Embodied Planning". A memory management system optimized for embodied planning via static-dynamic memory construction and KV cache re-computation, reducing memory overhead and improving inference speed.

No description.

Code release for ReaLM accepted by DAC 25

This is the official implementation of the algorithm part of "FPQVAR: Floating Point Quantization for Visual Autoregressive Model with FPGA Hardware Co-design"

No description.

Initial Implementation of "TEAM: Temporal-Spatial Consistency Guided Expert Activation for MoE Diffusion Language Model Acceleration".

DAC SDC 2023 Winner Designs

No description.

[NeurIPS'24] Official implement of "PrivCirNet: Efficient Private Inference via Block Circulant Transformation"

No description.

FPGA-based hardware accelerator for Vision Transformer (ViT), with Hybrid-Grained Pipeline.