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:Openai Openai node Streaming To Client
- Workflow:Pola rs Polars SQL Query Interface
- Workflow:Nautechsystems Nautilus trader Backtest with BacktestNode
- Workflow:Neuml Txtai Agent Execution
- Workflow:Microsoft Autogen Tool Augmented Agent
- Workflow:Predibase Lorax Server Deployment
- Workflow:Tensorflow Tfjs Sequential Model Training
- Workflow:Explodinggradients Ragas Agent Evaluation
- Workflow:Ollama Ollama Model Pull And Run
- Workflow:Intel Ipex llm RAG With LangChain
Principles
- Principle:Mit han lab Llm awq Distributed Model Serving
- Principle:LaurentMazare Tch rs Top K Prediction
- Principle:FlagOpen FlagEmbedding RetroMAE Pretraining
- Principle:CARLA simulator Carla Simulation Replay
- Principle:Tensorflow Serving Client Inference Validation
- Principle:DataTalksClub Data engineering zoomcamp Schema Normalization
- Principle:Explodinggradients Ragas Topic Adherence Evaluation
- Principle:Explodinggradients Ragas Multi Turn Evaluation Schema
- Principle:Pola rs Polars Aggregation Expression Building
- Principle:Sgl project Sglang Visual Input Preparation
Implementations
- Implementation:Predibase Lorax VLM Causal LM
- Implementation:Openai Evals Progress Class
- Implementation:Tensorflow Serving Util Test
- Implementation:MaterializeInc Materialize Repository Init
- Implementation:Alibaba MNN Protobuf Arena CC
- Implementation:Hiyouga LLaMA Factory DPO Zh Demo Data
- Implementation:BerriAI Litellm PostHog Logger
- Implementation:Microsoft Onnxruntime FloatTensorType Init
- Implementation:Ggml org Llama cpp Json Schema To Grammar Py
- Implementation:Shiyu coder Kronos WebUI App
Heuristics
- Heuristic:Marker Inc Korea AutoRAG Warning Deprecated Legacy QA Creation
- Heuristic:Ggml org Ggml Memory Allocation Strategy
- Heuristic:Mlflow Mlflow Batch Logging Size Limits
- Heuristic:PrefectHQ Prefect Retry Backoff Strategy
- Heuristic:Google deepmind Dm control Tolerance Reward Tuning
- Heuristic:Duckdb Duckdb Version Sync Across Files
- Heuristic:Marker Inc Korea AutoRAG Passage Filter Safety Minimum
- Heuristic:DistrictDataLabs Yellowbrick Model Fitted State Detection
- Heuristic:Huggingface Diffusers Memory Offloading Strategy
- Heuristic:Roboflow Rf detr Batch Size Memory Tradeoff
Environments
- Environment:Huggingface Diffusers Attention Backends
- Environment:ClickHouse ClickHouse CI Docker Environment
- Environment:Sgl project Sglang ROCm
- Environment:Protectai Modelscan Python Core Runtime
- Environment:Vibrantlabsai Ragas Google Drive Backend Environment
- Environment:Vllm project Vllm CPU Runtime
- Environment:EvolvingLMMs Lab Lmms eval API Credentials Environment
- Environment:MaterializeInc Materialize Buildkite CI Runtime
- Environment:CrewAIInc CrewAI Python Runtime Environment
- Environment:Open compass VLMEvalKit API Keys And Credentials