An obsidian plugin that helps to render a LaTeX-style pseudocode inside a code block.

Unified Reinforcement Learning Framework

为 Intel Arc GPU 电脑安装 Ollama

Llasa TTS 8B的WebUI，可以在本地构建自己的Demo

FlashMLA: Efficient MLA decoding kernels

Sends virtual input commands

A cross-platform GUI automation Python module for human beings. Used to programmatically control the mouse & keyboard.

Accelerate local LLM inference and finetuning (LLaMA, Mistral, ChatGLM, Qwen, DeepSeek, Mixtral, Gemma, Phi, MiniCPM, Qwen-VL, MiniCPM-V, etc.) on Intel XPU (e.g., local PC with iGPU and NPU, discr…

PyTorch version of Stable Baselines, reliable implementations of reinforcement learning algorithms.

Python wrapper for Xvfb, Xephyr and Xvnc

An API standard for single-agent reinforcement learning environments, with popular reference environments and related utilities (formerly Gym)

Install an OpenShift 4.x cluster

🛠「Watt Toolkit」是一个开源跨平台的多功能 Steam 工具箱。

A Flexible Framework for Experiencing Cutting-edge LLM Inference Optimizations

Official demos for package maliang

Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)

Accessible large language models via k-bit quantization for PyTorch.

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

This is the homepage of a new book entitled "Mathematical Foundations of Reinforcement Learning."

Fully open reproduction of DeepSeek-R1

🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.

Dify is an open-source LLM app development platform. Dify's intuitive interface combines AI workflow, RAG pipeline, agent capabilities, model management, observability features and more, letting yo…

🍒 Cherry Studio is a desktop client that supports for multiple LLM providers. Support deepseek-r1

A fast yet powerful Python Markdown parser with renderers and plugins.

PyMuPDF is a high performance Python library for data extraction, analysis, conversion & manipulation of PDF (and other) documents.

A community-maintained Python framework for creating mathematical animations.

《Pytorch实用教程》（第二版）无论是零基础入门，还是CV、NLP、LLM项目应用，或是进阶工程化部署落地，在这里都有。相信在本书的帮助下，读者将能够轻松掌握 PyTorch 的使用，成为一名优秀的深度学习工程师。

Fast and extensible multi-platform HTTP/1-2-3 web server with automatic HTTPS

中文对话0.2B小模型（ChatLM-Chinese-0.2B），开源所有数据集来源、数据清洗、tokenizer训练、模型预训练、SFT指令微调、RLHF优化等流程的全部代码。支持下游任务sft微调，给出三元组信息抽取微调示例。

A self-hosted alternative backend for the Obsidian Share Note plugin.