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:CarperAI Trlx RLHF Dialogue Alignment
- Workflow:Axolotl ai cloud Axolotl Full Finetuning Distributed
- Workflow:Trailofbits Fickling PyTorch Format Identification
- Workflow:Run llama Llama index RAG Query Pipeline
- Workflow:Vllm project Vllm Structured Output Generation
- Workflow:Microsoft Autogen Swarm Agent Handoff
- Workflow:Spcl Graph of thoughts Custom GoT Use Case Integration
- Workflow:PacktPublishing LLM Engineers Handbook RAG Inference
- Workflow:CARLA simulator Carla Sensor Data Collection
- Workflow:PacktPublishing LLM Engineers Handbook Digital Data ETL
Principles
- Principle:OpenHands OpenHands Ownership Establishment
- Principle:Arize ai Phoenix Evaluation Result Analysis
- Principle:CrewAIInc CrewAI Baseline Crew Configuration
- Principle:Apache Paimon Lance Distributed Analytics
- Principle:Kornia Kornia Edge Detection
- Principle:Farama Foundation Gymnasium Asynchronous Vector Execution
- Principle:Huggingface Diffusers Scheduler Selection
- Principle:Kornia Kornia Deep Edge Detection
- Principle:Openai Openai python API Error Handling
- Principle:Pola rs Polars Window Function Application
Implementations
- Implementation:PacktPublishing LLM Engineers Handbook VectorBaseDocument Bulk Insert
- Implementation:OpenRLHF OpenRLHF KDTrainer
- Implementation:Hpcaitech ColossalAI RewardModel
- Implementation:DistrictDataLabs Yellowbrick Rank2D Visualizer
- Implementation:Elevenlabs Elevenlabs python GetKnowledgeBaseFileResponseModel
- Implementation:Recommenders team Recommenders Affinity Matrix
- Implementation:Langfuse Langfuse Ingestion Event Schemas
- Implementation:Avhz RustQuant FractionalBrownianMotion
- Implementation:Kornia Kornia SmallSR
- Implementation:FlowiseAI Flowise Leads
Heuristics
- Heuristic:AnswerDotAI RAGatouille Auto Batch Size For Long Documents
- Heuristic:Facebookresearch Audiocraft Gradient Balancing For Multi Loss
- Heuristic:ARISE Initiative Robosuite XML Reset Method Tradeoff
- Heuristic:Dagster io Dagster Batch Size Tuning
- Heuristic:Apache Dolphinscheduler JDBC Security Blocklist
- Heuristic:Pola rs Polars Use Spawn Not Fork Multiprocessing
- Heuristic:NVIDIA NeMo Curator GPU Memory Resource Allocation
- Heuristic:Snorkel team Snorkel Minimum Three LFs
- Heuristic:PeterL1n BackgroundMattingV2 Mixed Precision Training
- Heuristic:Webdriverio Webdriverio Default Timeout Configuration
Environments
- Environment:Huggingface Alignment handbook BitsAndBytes CUDA
- Environment:Googleapis Python genai Gemini API Key Authentication
- Environment:Nightwatchjs Nightwatch Node 18 Runtime
- Environment:TobikoData Sqlmesh GitHub CICD Runner
- Environment:Apache Kafka Committer Tools Environment
- Environment:Bentoml BentoML BentoCloud Credentials
- Environment:Heibaiying BigData Notes Spark 2 4 Environment
- Environment:Bentoml BentoML Python Runtime
- Environment:Vllm project Vllm NVIDIA CUDA
- Environment:Huggingface Datasets SQL Dependencies