PACMAN Group, Tsinghua University

Parallel Architecture & Compiler technology of Mobile, Accelerated, and Networked systems

Popular repositories Loading

chitu Public

High-performance inference framework for large language models, focusing on efficiency, flexibility, and availability.

Python 3.4k 480
GeminiGraph Public

A computation-centric distributed graph processing system.

C++ 330 133
GridGraph Public

Out-of-core graph processing on a single machine.

C++ 130 59
PET Public

PET: Optimizing Tensor Programs with Partially Equivalent Transformations and Automated Corrections

C++ 125 10
Tree-KG Public

knowledge graph, llm, knowledge-intensive domains

114 5
FasterMoE Public archive

Python 89 14

BaGuaLu Public

Python 0 Apache-2.0 0 0 0 Updated Mar 3, 2026
chitu Public
High-performance inference framework for large language models, focusing on efficiency, flexibility, and availability.

Python 3,376 Apache-2.0 480 49 1 Updated Mar 3, 2026
RoMeo Public
Artifact for PPoPP'26 "RoMeo: Mitigating Dual-dimensional Outliers with Rotated Mixed Precision Quantization"

Python 4 MIT 0 0 0 Updated Jan 9, 2026
lab-guide Public
Everything about PACMAN!

14 3 0 0 Updated Dec 18, 2025
kaiyuan-mindformers Public Forked from mindspore-lab/mindformers
The training framework of PCMind-2.1-Kaiyuan-2B built on MindFormers

Python 15 Apache-2.0 22 0 0 Updated Dec 9, 2025
Kaiyuan-Spark Public
A scalable data preprocessing framework built on PySpark for LLM training

Python 23 Apache-2.0 1 0 1 Updated Dec 9, 2025
TriCache Public
A User-Transparent Block Cache Enabling High-Performance Out-of-Core Processing with In-Memory Programs

C++ 76 Apache-2.0 7 1 0 Updated Dec 8, 2025
Tree-KG Public
knowledge graph, llm, knowledge-intensive domains

114 5 5 0 Updated Jun 4, 2025
hypereca Public

C++ 2 0 0 0 Updated May 28, 2025
AIPerf Public

Python 5 MIT 1 4 0 Updated Nov 4, 2024