Ma Xinyin

Awesome-Efficient-LLM. A curated list for Efficient Large Language Models

LLM-Pruner. [NeurIPS 2023] LLM-Pruner: On the Structural Pruning of Large Language Models. Support Llama-3/3.1, Llama-2, LLaMA, BLOOM, Vicuna, Baichuan, TinyLlama, etc.

DeepCache. [CVPR 2024] DeepCache: Accelerating Diffusion Models for Free

dKV-Cache. [NeurIPS'25] dKV-Cache: The Cache for Diffusion Language Models

learning-to-cache. [NeurIPS 2024] Learning-to-Cache: Accelerating Diffusion Transformer via Layer Caching

CoT-Valve. CoT-Valve: Length-Compressible Chain-of-Thought Tuning

LLaMA-Pruning. Structural Pruning for LLaMA

PhysioNet. Deep learning based ECG classification

horseee.

Diffusion_DeepCache. JavaScript

AlphaDoge. MCTS based Go game agent

InfoHopNet-OpenBookQA. A Model for OpenBookQA Dataset.

MarkDuang. an easy implementation of Markdown

Music-Recommendation. Jupyter Notebook

weapp-server. Python

LessWord. A vocabulary cite~

NBA_search_engine. An NBA Search Engine

ML_basic_algorithm. Some implimentation of basic algorithm in Machine Learning

Weapp_BeautyBrain. JavaScript

WeiboCrawler. Java

ZJU_CG_Project. JavaScript

XRunner. Android App

prv_horseee.github.io. Github Pages template for academic personal websites, forked from mmistakes/minimal-mistakes

horseee.github.io. AcadHomepage: A Modern and Responsive Academic Personal Homepage

FlappyBird. An iOS app of FlappyBird

pytorch-pretrained-BERT. 📖The Big-&-Extending-Repository-of-Transformers: Pretrained PyTorch models for Google's BERT, OpenAI GPT & GPT-2, Google/CMU Transformer-XL.