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:ArroyoSystems Arroyo UDF Development
- Workflow:Risingwavelabs Risingwave Iceberg Lakehouse Ingestion
- Workflow:Truera Trulens RAG Evaluation With LangChain
- Workflow:Mit han lab Llm awq HuggingFace Model Export
- Workflow:Farama Foundation Gymnasium Policy Gradient Training
- Workflow:Ollama Ollama Custom Model Creation
- Workflow:Scikit learn Scikit learn Supervised Classification
- Workflow:OpenGVLab InternVL LoRA Finetuning
- Workflow:Apache Spark Building and Testing
- Workflow:PeterL1n BackgroundMattingV2 Training pipeline
Principles
- Principle:Apache Druid Spec Review and Task Submission
- Principle:Google deepmind Dm control Manipulation Episode Loop
- Principle:CrewAIInc CrewAI Tool Implementation
- Principle:Axolotl ai cloud Axolotl Configuration Validation
- Principle:FMInference FlexLLMGen Distributed Process Launching
- Principle:Ggml org Ggml Training Data Loading
- Principle:Ollama Ollama GGUF Model Conversion Qwen3
- Principle:Alibaba MNN Input Preprocessing
- Principle:Mage ai Mage ai Record Validation and Batching
- Principle:Ggml org Llama cpp Response Generation
Implementations
- Implementation:Langgenius Dify Analyze Component
- Implementation:Langchain ai Langchain HuggingFacePipeline
- Implementation:Romsto Speculative Decoding NGramStorage
- Implementation:Apache Druid Kubernetes Operator Main
- Implementation:Microsoft Onnxruntime OrtEnvironment
- Implementation:Google deepmind Dm control OSMesa Context
- Implementation:Nightwatchjs Nightwatch CreateClient Options
- Implementation:Infiniflow Ragflow AgentLogPage Component
- Implementation:InternLM Lmdeploy Core FloatingPoint
- Implementation:Apache Paimon FileIO
Heuristics
- Heuristic:Turboderp org Exllamav2 Attention Backend Selection
- Heuristic:Deepset ai Haystack BM25 Score Scaling
- Heuristic:Onnx Onnx Shape Inference Limitations
- Heuristic:Vibrantlabsai Ragas Temperature Sampling Strategy
- Heuristic:Lm sys FastChat Vicuna SFT Training Hyperparameters
- Heuristic:Alibaba ROLL Reward Clipping Normalization
- Heuristic:OWASP Www project top 10 for large language model applications SHA Pinning For GitHub Actions
- Heuristic:Datahub project Datahub Gradle Task Only
- Heuristic:Wandb Weave Sentinel Value Handling
- Heuristic:Marker Inc Korea AutoRAG GPU Memory Cleanup Pattern
Environments
- Environment:Anthropics Anthropic sdk python Python SDK Core Environment
- Environment:Apache Beam Java Build Environment
- Environment:Triton inference server Server GPU CUDA Runtime
- Environment:VainF Torch Pruning PyTorch Python Core
- Environment:ArroyoSystems Arroyo Python UDF Runtime
- Environment:Truera Trulens Snowflake Connector Environment
- Environment:Vllm project Vllm Benchmarks
- Environment:NVIDIA DALI PyTorch Environment
- Environment:NVIDIA NeMo Curator RAPIDS GPU Stack
- Environment:Sdv dev SDV GPU CUDA Support