Main Page
27,667
Total Pages
1,118
Workflows
7,697
Principles
16,832
Implementations
1,245
Heuristics
909
Environments
Welcome to Leeroopedia
Your ML & Data Knowledge Wiki. Best practices and expert-level knowledge for Machine Learning and Data Engineering, covering 1000+ frameworks and libraries from training to deployment.
Browse implementation patterns, configuration guides, debugging heuristics, and battle-tested defaults for frameworks like vLLM, DeepSpeed, Megatron-LM, FlashAttention, Triton, Unsloth, LangChain, and many more. Every page is structured so both humans and AI agents can find what they need fast.
Connect your AI coding agent. Plug Leeroopedia into your favorite coding agent, and let it build robust AI/ML systems autonomously:
- SuperML plugin — converts your AI coding agent into an expert ML engineer with agentic memory
- Leeroopedia MCP — search over best-practices and skills of ML/AI
- Kapso — experimentation platform for autonomous AI/ML software building
Browse by Category
| Category | Description | Browse |
|---|---|---|
| Workflows | Step-by-step processes and procedures | Browse All |
| Principles | Core ideas and foundational knowledge | Browse All |
| Implementations | Code-level details and modules | Browse All |
| Heuristics | Best practices and guidelines | Browse All |
| Environments | Setup and configuration guides | Browse All |
Explore Pages
Workflows
- Workflow:Ggml org Ggml GPT2 Text Generation
- Workflow:Huggingface Transformers Model Benchmarking
- Workflow:Haifengl Smile Data Loading Pipeline
- Workflow:OpenRLHF OpenRLHF PPO Ray Training
- Workflow:Intel Ipex llm LoRA Finetuning
- Workflow:Openclaw Openclaw Agent Message Loop
- Workflow:Trailofbits Fickling Pickle Safety Analysis
- Workflow:MarketSquare Robotframework browser JavaScript Extension
- Workflow:Eric mitchell Direct preference optimization DPO Preference Training
- Workflow:Avhz RustQuant Model Calibration
Principles
- Principle:Ggml org Llama cpp Configuration
- Principle:Iamhankai Forest of Thought BFS Forest Solving
- Principle:Interpretml Interpret Optimal Transport Selection
- Principle:Tensorflow Serving Executor Abstraction
- Principle:CrewAIInc CrewAI Project Scaffolding
- Principle:Facebookresearch Habitat lab HRL Configuration Composition
- Principle:Ggml org Llama cpp Model Loading
- Principle:Lance format Lance Schema Evolution
- Principle:DevExpress Testcafe Execution Parameter Tuning
- Principle:Microsoft Playwright Add Assertions
Implementations
- Implementation:ARISE Initiative Robosuite FourierHands
- Implementation:Ggml org Llama cpp Log
- Implementation:Ggml org Llama cpp Peg Parser Header
- Implementation:Langchain ai Langgraph Command Resume
- Implementation:Vibrantlabsai Ragas LiteLLM
- Implementation:Pytorch Serve Wav2Vec2 Handler
- Implementation:Apache Airflow StandaloneCommand Entrypoint
- Implementation:Huggingface Datatrove ExactDedupSignature
- Implementation:OWASP Www project top 10 for large language model applications ASIReporter Compile
- Implementation:Marker Inc Korea AutoRAG Chunker Start Chunking
Heuristics
- Heuristic:Liu00222 Open Prompt Injection Cosine Similarity Segmentation Threshold
- Heuristic:Openai Openai python Warning Deprecated Legacy Response
- Heuristic:Rapidsai Cuml Quantile Split Differences
- Heuristic:Openai Openai agents python Tool Choice Reset Prevents Loops
- Heuristic:Lm sys FastChat Vicuna SFT Training Hyperparameters
- Heuristic:Arize ai Phoenix Queue Clear Race Condition
- Heuristic:Google research Deduplicate text datasets HACKSIZE Overlap Buffer
- Heuristic:Zai org CogVideo Scheduler and Guidance Selection
- Heuristic:Ggml org Llama cpp GPU Layer Offloading Verification
- Heuristic:Trailofbits Fickling Force Flag Bypass
Environments
- Environment:Online ml River Python Runtime Environment
- Environment:Marker Inc Korea AutoRAG API Keys Configuration
- Environment:Dagster io Dagster Python 3 10 Runtime
- Environment:Elevenlabs Elevenlabs python Python Websockets
- Environment:Turboderp org Exllamav2 Build Toolchain
- Environment:Huggingface Alignment handbook DeepSpeed Multi Node
- Environment:Gretelai Gretel synthetics TensorFlow GPU Environment
- Environment:Recommenders team Recommenders Python Core Dependencies
- Environment:Langgenius Dify Docker Compose Environment
- Environment:Alibaba MNN HuggingFace Ecosystem Environment