AI-powered reverse engineering assistant that bridges IDA Pro with language models through MCP.

gem5 repository to study chiplet-based systems

Artifacts for "vCXLGen: Automated Synthesis and Verification of CXL Bridges for Heterogeneous Architectures", ASPLOS'26

Artifact for "C3: CXL Coherence Controllers for Heterogeneous Architectures" HPCA '26

GeminiFS: A Companion File System for GPUs

proof of concepts and experimental code for TFHE

Pure C++ Ver. of TFHE.

Zama's Homomorphic Processing Unit implementation on FPGA

example code for using DC QP for providing RDMA READ and WRITE operations to remote GPU memory

TFHE-rs: A Pure Rust implementation of the TFHE Scheme for Boolean and Integer Arithmetics Over Encrypted Data.

A Flexible Framework for Experiencing Heterogeneous LLM Inference/Fine-tune Optimizations

Build userspace NVMe drivers and storage applications with CUDA support

My learning notes for ML SYS.

A high-performance distributed file system designed to address the challenges of AI training and inference workloads.

DeepGEMM: clean and efficient BLAS kernel library on GPU

FlashMLA: Efficient Multi-head Latent Attention Kernels

llama.cpp to PyTorch Converter

PKU course materials on computer science and life science.

A fast GPU memory copy library based on NVIDIA GPUDirect RDMA technology

Tensors and Dynamic neural networks in Python with strong GPU acceleration

DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.

Let your Claude able to think

[HPCA'24] Smart-Infinity: Fast Large Language Model Training using Near-Storage Processing on a Real System

The official implementation of paper: SimLayerKV: A Simple Framework for Layer-Level KV Cache Reduction.

Port of Facebook's LLaMA model in C/C++