parrotsky

academic-kickstart

AttentioNN

All about attention in neural networks. Soft attention, attention maps, local and global attention and multi-head attention.

AutoDiCE

distributed CNN inference at the edge, extend ncnn with CUDA, MPI+OPENMP support.

AutoDiCE_examples

multinode examples for AutoDiCE

cavia

Code for "Fast Context Adaptation via Meta-Learning"

ChatGLM2-6B

ChatGLM2-6B: An Open Bilingual Chat LLM | 开源双语对话语言模型

convex_adversarial

A method for training neural networks that are provably robust to adversarial attacks.

DeepThings

A Portable C Library for Distributed CNN Inference on IoT Edge Clusters

fastllm

纯c++的全平台llm加速库，支持python调用，chatglm-6B级模型单卡可达10000+token / s，支持glm, llama, moss基座，手机端流畅运行

how-to-optimize-gemm

row-major matmul optimization

parrotsky/AutoDiCE

distributed CNN inference at the edge, extend ncnn with CUDA, MPI+OPENMP support.

parrotsky/academic-kickstart

parrotsky/AutoDiCE_examples

multinode examples for AutoDiCE

parrotsky/ChatGLM2-6B

ChatGLM2-6B: An Open Bilingual Chat LLM | 开源双语对话语言模型

parrotsky/convex_adversarial

A method for training neural networks that are provably robust to adversarial attacks.

parrotsky/DeepThings

A Portable C Library for Distributed CNN Inference on IoT Edge Clusters

parrotsky/fastllm

纯c++的全平台llm加速库，支持python调用，chatglm-6B级模型单卡可达10000+token / s，支持glm, llama, moss基座，手机端流畅运行

parrotsky/how-to-optimize-gemm

row-major matmul optimization

parrotsky/improved-diffusion

Release for Improved Denoising Diffusion Probabilistic Models

parrotsky/LearnCMake

parrotsky/LTP

[KDD'22] Learned Token Pruning for Transformers

parrotsky/mms

AlpaServe: Statistical Multiplexing with Model Parallelism for Deep Learning Serving (OSDI 23)

parrotsky/model_analyzer

Triton Model Analyzer is a CLI tool to help with better understanding of the compute and memory requirements of the Triton Inference Server models.

parrotsky/ncnn

ncnn is a high-performance neural network inference framework optimized for the mobile platform

parrotsky/NM-sparsity

parrotsky/openc910

OpenXuantie - OpenC910 Core

parrotsky/Optimizing-DGEMM-on-Intel-CPUs-with-AVX512F

Stepwise optimizations of DGEMM on CPU, reaching performance faster than Intel MKL eventually, even under multithreading.

parrotsky/parrotsky.github.io

parrotsky/PyTorch-Pretrained-ViT

Vision Transformer (ViT) in PyTorch

parrotsky/QC-Drug

parrotsky/RiskAwareLearning_VoltageOpt_DistGrid

parrotsky/starter-hugo-academic

🎓 Hugo Academic Theme 创建一个学术网站. Easily create a beautiful academic résumé or educational website using Hugo, GitHub, and Netlify.

parrotsky/sycl

SYCL for Vitis: Experimental fusion of triSYCL with Intel SYCL oneAPI DPC++ up-streaming effort into Clang/LLVM

parrotsky/SYCL-DNN

SYCL-DNN is a library implementing neural network algorithms written using SYCL

parrotsky/the-story-of-heads

This is a repository with the code for the ACL 2019 paper "Analyzing Multi-Head Self-Attention: Specialized Heads Do the Heavy Lifting, the Rest Can Be Pruned" and the ACL 2021 paper "Analyzing Source and Target Contributions to NMT Predictions".

parrotsky/Torch-Pruning

Structural Pruning for Model Acceleration

parrotsky/trt-samples-for-hackathon-cn

Simple samples for TensorRT programming

parrotsky/trt2023

parrotsky/Vitis-AI

Vitis AI is Xilinx’s development stack for AI inference on Xilinx hardware platforms, including both edge devices and Alveo cards.

parrotsky/vllm

A high-throughput and memory-efficient inference and serving engine for LLMs