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:Facebookresearch Audiocraft JASCO Conditioned Music Generation
- Workflow:Microsoft Autogen Swarm Agent Handoff
- Workflow:Googleapis Python genai Model Fine Tuning
- Workflow:Groq Groq python Text To Speech
- Workflow:Mlc ai Mlc llm Model Compilation
- Workflow:Evidentlyai Evidently Text Data Quality Evaluation
- Workflow:Huggingface Diffusers Checkpoint Conversion
- Workflow:OpenRLHF OpenRLHF Reward Model Training
- Workflow:Mlc ai Mlc llm REST API Serving
- Workflow:Arize ai Phoenix Span Annotation Pipeline
Principles
- Principle:AUTOMATIC1111 Stable diffusion webui Attention Optimization
- Principle:Huggingface Datatrove Token File Merging
- Principle:AUTOMATIC1111 Stable diffusion webui Training dataset preparation
- Principle:Sdv dev SDV Sequential Data Sampling
- Principle:Nightwatchjs Nightwatch Test Execution
- Principle:Deepset ai Haystack Pipeline Orchestration
- Principle:Arize ai Phoenix Evaluation Data Preparation
- Principle:Openai Openai node File Processing Verification
- Principle:Promptfoo Promptfoo Provider Registry
- Principle:Fastai Fastbook Learner Abstraction
Implementations
- Implementation:NVIDIA TransformerEngine TE LayerNorm
- Implementation:Hiyouga LLaMA Factory WebUI Chatter
- Implementation:Duckdb Duckdb Mbedtls ECP
- Implementation:Kserve Kserve TrainedModel Full CRD
- Implementation:Cohere ai Cohere python Vector Retrieval Pattern
- Implementation:Open compass VLMEvalKit DUDE
- Implementation:SeleniumHQ Selenium IEWebDriverManager
- Implementation:Spotify Luigi Sphinx Doc Configuration
- Implementation:TobikoData Sqlmesh FileExplorer Context
- Implementation:Haosulab ManiSkill FixedInspireHand
Heuristics
- Heuristic:Google research Deduplicate text datasets Parallel Job Scaling By Data Size
- Heuristic:CARLA simulator Carla Traffic Manager Sync Mode
- Heuristic:EvolvingLMMs Lab Lmms eval Memory Cleanup After Inference
- Heuristic:Snorkel team Snorkel NLP Preprocessor Memoization
- Heuristic:Scikit learn contrib Imbalanced learn Sampling Before Split Leakage
- Heuristic:Nautechsystems Nautilus trader Cache Buffer Interval Tuning
- Heuristic:Datahub project Datahub Validation Across All APIs
- Heuristic:PacktPublishing LLM Engineers Handbook Chunking Strategy By Content Type
- Heuristic:LLMBook zh LLMBook zh github io IGNORE INDEX Loss Masking
- Heuristic:Huggingface Open r1 Code Execution Timeout Strategy
Environments
- Environment:Deepset ai Haystack HuggingFace Model Environment
- Environment:ArroyoSystems Arroyo Rust Runtime
- Environment:Openai Openai python Python 3 9 Plus
- Environment:Fastai Fastbook Jupyter Notebook Environment
- Environment:Microsoft LoRA NLG Eval External Tools
- Environment:Huggingface Alignment handbook BitsAndBytes CUDA
- Environment:ArroyoSystems Arroyo Kubernetes Deployment
- Environment:Spcl Graph of thoughts Python 3 8 Runtime
- Environment:Recommenders team Recommenders Spark Environment
- Environment:BerriAI Litellm Provider API Credentials