Xiang-cd/codex
Lightweight coding agent that runs in your terminal
Second-year PHD at THU CST, major in generative model.
Lightweight coding agent that runs in your terminal
一个支持UI界面的清华云盘个人仓库批量下载, 链接批量下载,邮箱邮件批量下载工具,为毕业生批量迁移清华云盘内容和备份邮箱提供便利。
DeepGEMM: clean and efficient BLAS kernel library on GPU
收录主要由清华大学在校学生开发/维护的实用开源软件。
An open-source AI agent that brings the power of Gemini directly into your terminal.
my nas system setup doc.
CUDA Accelerated Robot Library
try different ai config system
a UI based workflow for manage arxiv papers with notion.
An unofficial implement of DiffEdit on stable-diffusion
fixed official code for paper "A Closer Look at Parameter-Efficient Tuning in Diffusion Models".
A Curated List of Awesome Works in World Modeling, Aiming to Serve as a One-stop Resource for Researchers, Practitioners, and Enthusiasts Interested in World Modeling.
LIBERO-PRO is the official repository of the LIBERO-PRO — an evaluation extension of the original LIBERO benchmark
Config files for my GitHub profile.
清华大学计算机系课程相关仓库
Cosmos-Predict2 is a collection of general-purpose world foundation models for Physical AI that can be fine-tuned into customized world models for downstream applications.
🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.
A terminal for a more modern age
Tile primitives for speedy kernels
ICLR2023-OpenReviewData, crawl in parallel
Modeling, training, eval, and inference code for OLMo
perform attention benchmark for different efficient attention.
TensorRT-LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and support state-of-the-art optimizations to perform inference efficiently on NVIDIA GPUs. TensorRT-LLM also contains components to create Python and C++ runtimes that orchestrate the inference execution in performant way.
A Flexible Framework for Experiencing Cutting-edge LLM Inference Optimizations
Collection of papers and resources on personalization of text to image models
official repo of feed-face (ICLR24)
A implementation of GPUProcessPoolExecutor to perform light weighted GPU parallel tasks.
tune sd using huggingface code HW3 of ML 2024 Fall
Efficient Triton Kernels for LLM Training