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:Marker Inc Korea AutoRAG RAG Pipeline Optimization
- Workflow:Lance format Lance Full Text Search
- Workflow:CARLA simulator Carla Simulation Recording and Replay
- Workflow:Apache Druid SQL Query Execution
- Workflow:AUTOMATIC1111 Stable diffusion webui Image to image generation
- Workflow:Hiyouga LLaMA Factory LoRA SFT Finetuning
- Workflow:Spotify Luigi Central Scheduler Deployment
- Workflow:Sktime Pytorch forecasting TFT Demand Forecasting
- Workflow:OpenRLHF OpenRLHF Knowledge Distillation
- Workflow:Run llama Llama index ReAct Agent
Principles
- Principle:Mit han lab Llm awq Quantized Weight Loading
- Principle:Nightwatchjs Nightwatch Multi Page Composition
- Principle:Tencent Ncnn Foreign Model Conversion
- Principle:Lance format Lance Vector Index Building
- Principle:Eventual Inc Daft Window Functions
- Principle:Sktime Pytorch forecasting Dense Encoder Decoder
- Principle:EvolvingLMMs Lab Lmms eval Media Handling
- Principle:Ggml org Llama cpp Server Build
- Principle:Haotian liu LLaVA Checkpoint Extraction
- Principle:MaterializeInc Materialize Local Test Execution
Implementations
- Implementation:Risingwavelabs Risingwave DynMethods
- Implementation:Openclaw Openclaw ResolveChannelGroupRequireMention
- Implementation:FlowiseAI Flowise Typography
- Implementation:Shiyu coder Kronos QlibDataPreprocessor Usage
- Implementation:Mlc ai Mlc llm Serve Data
- Implementation:Farama Foundation Gymnasium GAE Computation
- Implementation:Deepset ai Haystack SentenceTransformersDocumentEmbedder
- Implementation:Triton inference server Server L0 Storage S3 Local Test
- Implementation:Open compass VLMEvalKit ChartMimic Chart Type And Color
- Implementation:Vllm project Vllm CUMem Allocator
Heuristics
- Heuristic:Wandb Weave Retry And Error Handling
- Heuristic:Allenai Open instruct Disable Dropout In RL
- Heuristic:Facebookresearch Audiocraft Generation Parameter Defaults
- Heuristic:Ggml org Llama cpp Thread Count Tuning
- Heuristic:Farama Foundation Gymnasium Sync Vs Async VectorEnv Selection
- Heuristic:Diagram of thought Diagram of thought Strict Vs Flexible Critic Rigor
- Heuristic:CarperAI Trlx Batch Size Tuning
- Heuristic:Huggingface Open r1 Reward Function Tuning
- Heuristic:Snorkel team Snorkel Precision Init Prior
- Heuristic:Zai org CogVideo CPU Offload Strategy
Environments
- Environment:Snorkel team Snorkel Dask Distributed
- Environment:NVIDIA NeMo Aligner NeMo Framework GPU Environment
- Environment:Marker Inc Korea AutoRAG GPU PyTorch Environment
- Environment:Protectai Modelscan TensorFlow Optional
- Environment:Langchain ai Langchain Unit Test Network Isolation
- Environment:Iamhankai Forest of Thought OpenAI API Credentials
- Environment:Nightwatchjs Nightwatch Android Mobile Testing
- Environment:OpenRLHF OpenRLHF CUDA GPU Environment
- Environment:Iterative Dvc Git SCM Environment
- Environment:OpenRLHF OpenRLHF Flash Attention Environment