《AI全栈-全网优秀资源搜集站》:搜集全网优秀资源,记载工程实践问题的解决策略与关键要点,分享各种实用案例,追踪前沿技术发展,囊括 AI 全栈知识,涵盖大模型、编程技术、机器学习、深度学习、强化学习、图神经网络、语音识别、NLP 及图像识别等领域
Repository Index
132,241 visible repositories in the index
217–240 of 277 · Most stars
Pure Rust + CUDA LLM inference engine — no PyTorch, OpenAI-compatible, serves Qwen3 to Kimi-K2
- inference
- kimi
- llm-serving
- model-serving
Tasks Assessing Protein Embeddings (TAPE), a set of five biologically relevant semi-supervised learning tasks spread across different domains of protein biology.
- deep-learning
- protein-sequences
- protein-structure
- semi-supervised-learning
Contrib package for Stable-Baselines3 - Experimental reinforcement learning (RL) code
- reinforcement-learning
- stable-baselines
- pytorch
- rl
Integrating the Best of TF into PyTorch, for Machine Learning, Natural Language Processing, and Text Generation. This is part of the CASL project: http://casl-project.ai/
The prime repository for state-of-the-art Multilingual Question Answering research and development.
- ibm
- ibm-research-ai
- machine-learning
- natural-language-processing
[ICCV 2025] Official code of DeepMesh: Auto-Regressive Artist-mesh Creation with Reinforcement Learning
- 3d
- aigc
- dpo
- generative-model
A no-code 3D playground to explore, design, and interact with Agentic AI systems
- 3d-simulation
- ai
- ai-agents
- autonomous-agents
A most Frontend Collection and survey of vision-language model papers, and models GitHub repository. Continuous updates.
Long-RL: Scaling RL to Long Sequences (NeurIPS 2025)
- efficient-ai
- large-language-models
- long-sequence
- multi-modality
Simple implementation of OpenAI CLIP model in PyTorch.
- clip-model
- pytorch
- openai-clip
- paper
Texas holdem OpenAi gym poker environment with reinforcement learning based on keras-rl. Includes virtual rendering and montecarlo for equity calculation.
- poker
- openai-gym
- holdem
- reinforcement-learning
Salesforce open-source LLMs with 8k sequence length.
- llm
- language-model
- large-language-models
- nlp
The PyTorch implementation of Generative Pre-trained Transformers (GPTs) using Kolmogorov-Arnold Networks (KANs) for language modeling
- gpt
- kanformers
- kolmogorov-arnold-networks
- kolmogorov-arnold-representation
A PyTorch Lightning solution to training OpenAI's CLIP from scratch.
Serverless LLM Serving for Everyone.
- large-language-models
- model-as-a-service
- model-serving
- serverless-inference
All your AI providers, machines, and agent harnesses in one place. Free & native
- ai-agents
- autonomous-agents
- coding-assistant
- containerization
Development workflows for Claude Code that keep broad exploration focused on the outcome you approved.
Multi-model orchestration layer for Claude Code — the frontier model plans, cheaper models execute, verification guards quality. One-prompt install.
Trinity-RFT is a general-purpose, flexible and scalable framework designed for reinforcement fine-tuning (RFT) of large language models (LLM).
Machine learning Guide. Learn all about Machine Learning Tools, Libraries, Frameworks, Large Language Models (LLMs), and Training Models.
- python
- deep-learning
- machine-learning-library
- machinelearning
Open-source self-hosted AI agent runtime and multi-agent framework for autonomous agent swarms. Agent memory, MCP tools, schedules, delegation, and 23+ LLM providers (Claude, GPT, Gemini, OpenRouter, Ollama). A practical Claude Code and LangChain alternative.
ns3-gym - The Playground for Reinforcement Learning in Networking Research
- ns3
- gym-environment
- openai-gym
- reinforcement-learning
USP: Unified (a.k.a. Hybrid, 2D) Sequence Parallel Attention for Long Context Transformers Model Training and Inference
- attention-is-all-you-need
- llm-inference
- llm-training
- pytorch