17-day current streak·28-day longest streak
Hi there 👋 <!-- XuehaiPan/XuehaiPan is a ✨ _special_ ✨ repository because its README.md (this file) appears on your GitHub profile. Here are some ideas to get you started: 🔭…
Hi there 👋
<!--
XuehaiPan/XuehaiPan is a ✨ _special_ ✨ repository because its README.md (this file) appears on your GitHub profile.
Here are some ideas to get you started:
- 🔭 I’m currently working on ...
- 🌱 I’m currently learning ...
- 👯 I’m looking to collaborate on ...
- 🤔 I’m looking for help with ...
- 💬 Ask me about ...
- 📫 How to reach me: ...
- 😄 Pronouns: ...
- ⚡ Fun fact: ...
Xuehai Pan (/ʃwɛˈhaɪ pæn/, 潘学海 in Mandarin, [[email protected]](mailto:[email protected])) is a final-year Ph.D. student in Applied Computer Science at Peking University.
His research interests lie in the intersection of Reinforcement Learning, Multi-Agent Systems, and Distributed Computing, with a focus on developing _scalable_ and _automated_ algorithms and exploring their theoretical and practical aspects.
He has a solid background in both research and engineering, having obtained a B.S. degree in _Physics_ with honors and a B.S. degree in _Computer Science_ (double major) from Peking University before pursuing his Ph.D. degree.
His academic journey is embellished with achievements such as winning gold medals in the Chinese Physics Olympiad (CPhO) and the Asian Physics Olympiad (APhO) during high school.
Xuehai is now working on pioneering research in the development of Large Language Models (LLMs) while ensuring they align with human intentions and values through AI Alignment techniques (essentially balancing between helpfulness and harmlessness).
Specifically, he is exploring automated data syntactic, red teaming, and evolutional training via multi-agent interaction and self-play.
The ultimate goal is to build a scalable and fully automated system, including training, evaluation, inference, and governance.
Beyond academia, Xuehai is an open-source enthusiast and an active contributor to influential projects such as PyTorch, CPython, Ray, Transformers, DeepSpeed, Gymnasium (formerly OpenAI Gym), PyBind11 (C++ bindings for Python), PyO3 (Rust bindings for Python), Conda, Homebrew, etc.
He enjoys dedicating his spare time to helping people and sharing knowledge in the community, further enriching his impact beyond his research pursuits.
-
nvitop ★ PINNED
An interactive NVIDIA-GPU process viewer and beyond, the one-stop solution for GPU process management.
Python ★ 7.0k 1d agoExplain → -
safe-rlhf ★ PINNED ⑂
Safe-RLHF: Constrained Value Alignment via Safe Reinforcement Learning from Human Feedback
Python ★ 4 6mo agoExplain → -
torchopt ★ PINNED ⑂
TorchOpt is a high-performance optimizer library built upon PyTorch for easy implementation of functional optimization and gradient-based meta-learning.
Python ★ 2 2y agoExplain → -
optree ★ PINNED ⑂
OpTree: Optimized PyTree Utilities
Python ★ 0 1d agoExplain → -
pytorch ★ PINNED ⑂
Tensors and Dynamic neural networks in Python with strong GPU acceleration
Python ★ 1 1d agoExplain → -
ray ★ PINNED ⑂
An open source framework that provides a simple, universal API for building distributed applications. Ray is packaged with RLlib, a scalable reinforcement learning library, and Tune, a scalable hyperparameter tuning library.
Python ★ 1 5d agoExplain → -
Dev-Setup
Automation scripts for setting up a basic development environment.
Shell ★ 121 8d agoExplain → -
LaTeX-Templates
A collection of LaTeX templates in English/Chinese, with VS Code settings for LaTeX Workshop.
TeX ★ 69 9mo agoExplain → -
mate
MATE: the Multi-Agent Tracking Environment.
Python ★ 47 3y agoExplain → -
Soft-Actor-Critic
PyTorch Implementation of Soft Actor-Critic Algorithm
Python ★ 12 5y agoExplain → -
XuehaiPan
No description.
★ 8 1y agoExplain → -
torchrec ⑂
Pytorch domain library for recommendation systems
Python ★ 3 1y agoExplain → -
homebrew-core ⑂
🍻 Default formulae for the missing package manager for macOS
Ruby ★ 2 5d agoExplain → -
brew ⑂
🍺 The missing package manager for macOS (or Linux)
Ruby ★ 2 5d agoExplain → -
psutil ⑂
Cross-platform lib for process and system monitoring in Python
Python ★ 2 29d agoExplain → -
nvtop ⑂
NVIDIA GPUs htop like monitoring tool
C ★ 2 1y agoExplain → -
cpython ⑂
The Python programming language
Python ★ 1 1d agoExplain → -
jax ⑂
Composable transformations of Python+NumPy programs: differentiate, vectorize, JIT to GPU/TPU, and more
Python ★ 1 5d agoExplain → -
transformers ⑂
🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.
Python ★ 1 5d agoExplain → -
brew-install ⑂
📥 Homebrew (un)installer
Shell ★ 1 7d agoExplain → -
tensorflow ⑂
An Open Source Machine Learning Framework for Everyone
C++ ★ 1 21d agoExplain → -
conda ⑂
OS-agnostic, system-level binary package manager and ecosystem
Python ★ 1 21d agoExplain → -
nvidia-ml-py
A community-maintained mirror of the `nvidia-ml-py` package on PyPI to view the changes easier. PLEASE DO NOT FILE ANY BUG REPORT HERE.
Python ★ 1 21d agoExplain → -
torch-xla ⑂
Enabling PyTorch on XLA Devices (e.g. Google TPU)
C++ ★ 1 29d agoExplain → -
ranger ⑂
A VIM-inspired filemanager for the console
Python ★ 1 1mo agoExplain → -
llama.cpp ⑂
LLM inference in C/C++
C++ ★ 1 6mo agoExplain → -
flash-mla ⑂
No description.
C++ ★ 1 1y agoExplain → -
auditwheel ⑂
Auditing and relabeling cross-distribution Linux wheels.
Python ★ 1 1y agoExplain → -
TheAlgorithmsPython ⑂
All Algorithms implemented in Python
★ 1 2y agoExplain → -
baichuan-7B ⑂
A large-scale 7B pretraining language model developed by Baichuan
Python ★ 1 3y agoExplain → -
malib ⑂
A parallel framework for population-based multi-agent reinforcement learning.
Python ★ 1 3y agoExplain → -
alpa ⑂
Auto parallelization for large-scale neural networks
Python ★ 1 3y agoExplain → -
go-nvml ⑂
Go Bindings for the NVIDIA Management Library (NVML)
C ★ 1 3y agoExplain → -
MARLlib ⑂
No description.
Python ★ 1 3y agoExplain → -
torchrl ⑂
A modular, primitive-first, python-first PyTorch library for Reinforcement Learning.
Python ★ 1 3y agoExplain → -
LaTeX-Workshop ⑂
Boost LaTeX typesetting efficiency with preview, compile, autocomplete, colorize, and more.
TypeScript ★ 1 3y agoExplain → -
typeshed ⑂
Collection of library stubs for Python, with static types
Python ★ 0 1d agoExplain → -
tilelang ⑂
Domain-specific language designed to streamline the development of high-performance GPU/CPU/Accelerators kernels
Python ★ 0 5d agoExplain → -
sglang ⑂
SGLang is a fast serving framework for large language models and vision language models.
Python ★ 0 5d agoExplain → -
pyo3 ⑂
Rust bindings for the Python interpreter
Rust ★ 0 5d agoExplain → -
safetensors ⑂
Simple, safe way to store and distribute tensors
Rust ★ 0 5d agoExplain → -
triton ⑂
Development repository for the Triton language and compiler
MLIR ★ 0 5d agoExplain → -
vllm ⑂
A high-throughput and memory-efficient inference and serving engine for LLMs
Python ★ 0 5d agoExplain → -
uv ⑂
An extremely fast Python package and project manager, written in Rust.
Rust ★ 0 5d agoExplain → -
pybind11 ⑂
Seamless operability between C++11 and Python
C++ ★ 0 5d agoExplain → -
ruff ⑂
An extremely fast Python linter, written in Rust.
Rust ★ 0 5d agoExplain → -
typing-extensions ⑂
Backported and experimental type hints for Python
Python ★ 0 7d agoExplain → -
gpustat ⑂
📊 A simple command-line utility for querying and monitoring GPU status
Python ★ 0 21d agoExplain → -
streamlit ⑂
Streamlit — A faster way to build and share data apps.
Python ★ 0 21d agoExplain → -
rust ⑂
Empowering everyone to build reliable and efficient software.
Rust ★ 0 21d agoExplain → -
nvitop-feedstock ⑂
A conda-smithy repository for nvitop.
★ 0 1mo agoExplain → -
optree-feedstock ⑂
A conda-smithy repository for optree.
★ 0 1mo agoExplain → -
DeepSpeed ⑂
DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.
Python ★ 0 3mo agoExplain → -
gymnasium ⑂
A standard API for reinforcement learning and a diverse set of reference environments (formerly Gym)
Python ★ 0 3mo agoExplain → -
rustree
A personal project to learn Rust-Python interaction.
Python ★ 0 2mo agoExplain → -
openai-python-sdk ⑂
The official Python library for the OpenAI API
Python ★ 0 6mo agoExplain → -
nvitop-exporter-feedstock ⑂
A conda-smithy repository for nvitop-exporter.
★ 0 6mo agoExplain → -
mypy ⑂
Optional static typing for Python
Python ★ 0 6mo agoExplain → -
openai-harmony ⑂
Renderer for the harmony response format to be used with gpt-oss
Rust ★ 0 7mo agoExplain → -
addlicense ⑂
A program which ensures source code files have copyright license headers by scanning directory patterns recursively
Go ★ 0 7mo agoExplain → -
pytorch-test-infra ⑂
This repository hosts code that supports the testing infrastructure for the PyTorch organization. For example, this repo hosts the logic to track disabled tests and slow tests, as well as our continuation integration jobs HUD/dashboard.
TypeScript ★ 0 10mo agoExplain → -
omnisafe ⑂
OmniSafe is a comprehensive and reliable benchmark for safe reinforcement learning.
Python ★ 0 1y agoExplain → -
tuna-mirror-help ⑂
Source code of the web interface of https://mirrors.tuna.tsinghua.edu.cn/
HTML ★ 0 11mo agoExplain → -
flax ⑂
Flax is a neural network library for JAX that is designed for flexibility.
Jupyter Notebook ★ 0 1y agoExplain → -
conda-forge-staged-recipes ⑂
A place to submit conda recipes before they become fully fledged conda-forge feedstocks
Python ★ 0 1y agoExplain → -
accelerate ⑂
🚀 A simple way to launch, train, and use PyTorch models on almost any device and distributed configuration, automatic mixed precision (including fp8), and easy-to-configure FSDP and DeepSpeed support
Python ★ 0 1y agoExplain → -
setuptools ⑂
Official project repository for the Setuptools build system
Python ★ 0 1y agoExplain → -
rich ⑂
Rich is a Python library for rich text and beautiful formatting in the terminal.
Python ★ 0 1y agoExplain → -
deep-ep ⑂
DeepEP: an efficient expert-parallel communication library
★ 0 1y agoExplain → -
smolagents ⑂
🤗 smolagents: a barebones library for agents. Agents write python code to call tools and orchestrate other agents.
★ 0 1y agoExplain → -
isort ⑂
A Python utility / library to sort imports.
Python ★ 0 1y agoExplain → -
torchao ⑂
PyTorch native quantization and sparsity for training and inference
Python ★ 0 1y agoExplain → -
nvidia-ml-py-feedstock ⑂
A conda-smithy repository for nvidia-ml-py.
★ 0 1y agoExplain → -
optax ⑂
Optax is a gradient processing and optimization library for JAX.
★ 0 2y agoExplain → -
MOSS ⑂
An open-source tool-augmented conversational language model from Fudan University
Python ★ 0 3y agoExplain → -
text-generation-inference ⑂
Large Language Model Text Generation Inference
★ 0 2y agoExplain → -
Megatron-LM ⑂
Ongoing research training transformer models at scale
★ 0 2y agoExplain → -
FastChat ⑂
An open platform for training, serving, and evaluating large language models. Release repo for Vicuna and FastChat-T5.
Python ★ 0 2y agoExplain → -
more-itertools ⑂
More routines for operating on iterables, beyond itertools
★ 0 3y agoExplain → -
flake8-pyi ⑂
A plugin for Flake8 that provides specializations for type hinting stub files
★ 0 3y agoExplain → -
tensordict ⑂
TensorDict is a pytorch dedicated tensor container.
Python ★ 0 3y agoExplain → -
safety-gymnasium ⑂
Safety-Gymnaisum is a highly scalable and customizable safe reinforcement learning environment library.
Python ★ 0 2y agoExplain → -
mamba ⑂
The Fast Cross-Platform Package Manager
C++ ★ 0 3y agoExplain → -
pytorch-builder ⑂
Continuous builder and binary build scripts for pytorch
Shell ★ 0 2y agoExplain → -
Trail ▣
Software Engineering Course Project
Vue ★ 0 4y agoExplain → -
pkuthss ⑂
LaTeX template for dissertations in Peking University
TeX ★ 0 3y agoExplain → -
xuehaipan.github.io
No description.
HTML ★ 0 6y agoExplain → -
DocumentBasedQuestionAnswering
Web Data Mining Course Project
HTML ★ 0 7y agoExplain → -
CoherenceAnalysis
Web Data Mining Course Project
Python ★ 0 7y agoExplain → -
ChineseWordSegmentation
Intro. to Natural Language Processing Course Project
Python ★ 0 8y agoExplain → -
ValueRangeAnalyst
Compiler Design Course Project
Python ★ 0 7y agoExplain → -
GomokuWithChat
Java Programming Course Project
Java ★ 0 8y agoExplain → -
SolarSystemSimulationWithOpenGL
No description.
C++ ★ 0 8y agoExplain → -
DataStructureImpl
No description.
C++ ★ 0 8y agoExplain → -
2dConvWithOpenCL
No description.
C++ ★ 0 8y agoExplain → -
Gomoku
No description.
Java ★ 0 8y agoExplain →
No repos match these filters.