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:Spcl Graph of thoughts GoT Keyword Counting Pipeline
- Workflow:CrewAIInc CrewAI Hierarchical Crew Execution
- Workflow:PacktPublishing LLM Engineers Handbook Dataset Generation
- Workflow:Scikit learn Scikit learn Supervised Classification
- Workflow:Apache Beam Portable Pipeline Submission
- Workflow:BerriAI Litellm Proxy Server Deployment
- Workflow:Confident ai Deepeval Component Level LLM Evaluation
- Workflow:Arize ai Phoenix Prompt Management Pipeline
- Workflow:Dagster io Dagster DSPy Optimization
- Workflow:Langchain ai Langgraph Functional API Workflow
Principles
- Principle:Allenai Open instruct Model Configuration
- Principle:Vllm project Vllm Constrained Sampling Configuration
- Principle:Huggingface Diffusers Training Configuration
- Principle:Unstructured IO Unstructured Ingest Processing Configuration
- Principle:Tensorflow Tfjs Model Evaluation And Deployment
- Principle:Kserve Kserve InferenceGraph Specification
- Principle:Iterative Dvc Vega Lite Template Application
- Principle:Nautechsystems Nautilus trader Strategy Configuration
- Principle:BerriAI Litellm Environment Configuration
- Principle:Microsoft Onnxruntime Inference Session Creation
Implementations
- Implementation:Huggingface Alignment handbook ORPOTrainer Usage
- Implementation:NVIDIA TransformerEngine Ops Fused Forward Linear Bias Activation
- Implementation:Huggingface Datatrove TokenStats
- Implementation:Vllm project Vllm Structured Output Parsing
- Implementation:Deepseek ai Janus Apply Sft Template
- Implementation:NVIDIA TransformerEngine Initialize UB
- Implementation:Openai Openai python Response Custom Tool Call Input Done
- Implementation:Scikit learn Scikit learn KernelRidge
- Implementation:Facebookresearch Audiocraft EncodecModel decode
- Implementation:Open compass VLMEvalKit OCR Reasoning Utils
Heuristics
- Heuristic:MarketSquare Robotframework browser MacOS Sonoma Startup Delay
- Heuristic:ARISE Initiative Robosuite Numba BSOD Workaround
- Heuristic:Huggingface Datatrove VLLM Startup Optimization
- Heuristic:ARISE Initiative Robomimic Checkpoint Selection Strategy
- Heuristic:Marker Inc Korea AutoRAG Empty Result Fallback
- Heuristic:Heibaiying BigData Notes Spark Streaming Local Threads Tip
- Heuristic:Openai Openai python Retry Backoff Strategy
- Heuristic:Marker Inc Korea AutoRAG Hybrid Retrieval Score Normalization
- Heuristic:Bigscience workshop Petals Short Inference Pool Merging
- Heuristic:TA Lib Ta lib python Thread Safety With Abstract API
Environments
- Environment:Evidentlyai Evidently SQL Storage Environment
- Environment:ArroyoSystems Arroyo Kubernetes Deployment
- Environment:Openai Openai python Azure OpenAI
- Environment:Vespa engine Vespa Cosign Sigstore Signing
- Environment:Microsoft DeepSpeedExamples RLHF Training Environment
- Environment:Iterative Dvc Remote Storage Backends
- Environment:Kserve Kserve Kubernetes Cluster
- Environment:OpenRLHF OpenRLHF vLLM Environment
- Environment:OWASP Www project top 10 for large language model applications PR Description Generator Runtime
- Environment:Open compass VLMEvalKit GPU CUDA Environment