Stars
MedicalGPT: Training Your Own Medical GPT Model with ChatGPT Training Pipeline. 训练医疗大模型，实现了包括增量预训练(PT)、有监督微调(SFT)、RLHF、DPO、ORPO、GRPO。
Multimodal RL training framework for diffusion & omni models
An interactive NVIDIA-GPU process viewer and beyond, the one-stop solution for GPU process management.
[TPAMI 2025] ViewCrafter: Taming Video Diffusion Models for High-fidelity Novel View Synthesis
Nanite-Style Gaussian Splatting Render
DeepEP: an efficient expert-parallel communication library
reverse engineering Gemini's SynthID detection
Semantic search over videos using Gemini Embedding 2 or Qwen3-VL.
[GDGS] A real-time 3D Gaussian Splatting (3DGS) rendering plugin for the Godot Engine. Godot引擎的实时3DGS渲染插件
Convert math-rich Typst project to Microsoft Word format
A beautiful config generator for Ghostty terminal.
lesj0610 / flash-attention
Forked from Dao-AILab/flash-attentionFast and memory-efficient exact attention
Lecture Notes for ECE 370: Signals and Systems at The University of Alabama
企业网络协议转换器，将单独的协议订阅链接转换为 Mihomo 内核 YAML 配置文件
Quickstart template for GDExtension development with Godot
[CVPR 2025] Efficient Video Super-Resolution for Real-time Rendering with Decoupled G-buffer Guidance
Unlock your displays on your Mac! Flexible HiDPI scaling, XDR/HDR extra brightness, virtual screens, DDC control, extra dimming, PIP/streaming, EDID override and lots more!
Authentication utility for srun4000 (auth.tsinghua.edu.cn / net.tsinghua.edu.cn / Tsinghua-IPv4)
清华大学计算机系课程攻略 Guidance for courses in Department of Computer Science and Technology, Tsinghua University
A customizable TUI display/login manager written in Rust 🐒
GPU & Accelerator process monitoring for AMD, Apple, Huawei, Intel, NVIDIA and Qualcomm
A High-Performance LLM Inference Engine with vLLM-Style Continuous Batching
A free, modern engine for visual novels | 自由，现代化的视觉小说引擎
Everything about the SmolLM and SmolVLM family of models
High-performance inference framework for large language models, focusing on efficiency, flexibility, and availability.