Main Page
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:Huggingface Optimum Automatic Tensor Parallelization
- Workflow:Marker Inc Korea AutoRAG Evaluation Data Creation
- Workflow:Pyro ppl Pyro Discrete Enumeration
- Workflow:Huggingface Datasets Hub Publishing
- Workflow:Danijar Dreamerv3 Evaluation Only
- Workflow:Langchain ai Langgraph Human in the Loop Agent
- Workflow:Onnx Onnx External Data Handling
- Workflow:CarperAI Trlx PPO Sentiment Training
- Workflow:CarperAI Trlx RLHF Summarization Pipeline
- Workflow:Microsoft Onnxruntime Nodejs Inference
Principles
- Principle:OWASP Www project top 10 for large language model applications Threat Modeling Against Top 10
- Principle:Astronomer Astronomer cosmos Profile Configuration
- Principle:Microsoft Agent framework Workflow Graph Construction
- Principle:Ggml org Llama cpp Configuration
- Principle:Huggingface Datatrove HTML Text Extraction
- Principle:Bitsandbytes foundation Bitsandbytes CI CD Build Pipeline
- Principle:Anthropics Anthropic sdk python Provider Selection And Dependencies
- Principle:NVIDIA DALI Video Spatial Crop
- Principle:Farama Foundation Gymnasium Observation Wrapping
- Principle:Scikit learn contrib Imbalanced learn Synthetic Minority Oversampling
Implementations
- Implementation:PeterL1n BackgroundMattingV2 Load pretrained deeplabv3 state dict
- Implementation:Huggingface Optimum GPTQQuantizer Convert Model
- Implementation:CrewAIInc CrewAI RAG PDF Loader
- Implementation:Ggml org Ggml Webgpu wgsl preprocessor
- Implementation:FlagOpen FlagEmbedding BGE VL Eval CIRCO
- Implementation:Facebookresearch Habitat lab Gym Definitions
- Implementation:Langgenius Dify Doc Paths Types
- Implementation:MaterializeInc Materialize Cut Release Tag
- Implementation:Haosulab ManiSkill PullCubeTool
- Implementation:Astronomer Astronomer cosmos Get Dataset Alias Name
Heuristics
- Heuristic:Intel Ipex llm DeepSpeed Tensor Parallel Tips
- Heuristic:Lance format Lance Encoding Compression Thresholds
- Heuristic:MaterializeInc Materialize Dbt Transaction Disable
- Heuristic:Apache Kafka JVM GC Tuning Defaults
- Heuristic:Haotian liu LLaVA Gradient Checkpointing Memory Optimization
- Heuristic:Wandb Weave Payload Size Limits
- Heuristic:Lm sys FastChat Vicuna SFT Training Hyperparameters
- Heuristic:Spotify Luigi Parameter Propagation Decorators
- Heuristic:Microsoft Autogen Graph Validation Rules
- Heuristic:Tensorflow Serving Warning Deprecated CreateTfrtSavedModel Raw
Environments
- Environment:NVIDIA DALI PyTorch Environment
- Environment:Langfuse Langfuse Redis 7 Queue Cache
- Environment:Fastai Fastbook Jupyter Notebook Environment
- Environment:Elevenlabs Elevenlabs python Python Httpx
- Environment:ChenghaoMou Text dedup Suffix Array External Tools
- Environment:Huggingface Optimum Accelerated Inference Environment
- Environment:Google deepmind Dm control Python MuJoCo Runtime
- Environment:Explodinggradients Ragas Google Drive Backend Environment
- Environment:Huggingface Open r1 Slurm Cluster
- Environment:Openclaw Openclaw Mintlify Documentation Platform