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:Kornia Kornia Differentiable Image Augmentation
- Workflow:Ray project Ray Cross Language Invocation
- Workflow:SeldonIO Seldon core AB Testing Experiment
- Workflow:Langchain ai Langgraph Persistence and Memory Setup
- Workflow:Spotify Luigi Hadoop MapReduce Pipeline
- Workflow:Apache Shardingsphere Dynamic Rule Configuration Change
- Workflow:Speechbrain Speechbrain Speech Separation Training
- Workflow:Huggingface Datasets Dataset Loading and Exploration
- Workflow:Anthropics Anthropic sdk python Tool Use Integration
- Workflow:SeldonIO Seldon core HuggingFace Model Serving
Principles
- Principle:Langgenius Dify Prompt Template Design
- Principle:OpenGVLab InternVL Packed Sequence Training
- Principle:Ggml org Llama cpp Chat Template Application
- Principle:Nightwatchjs Nightwatch Component Plugin Installation
- Principle:Datajuicer Data juicer Column Wise Distribution Analysis
- Principle:Avhz RustQuant Probability Distributions
- Principle:NVIDIA NeMo Curator Pairwise Similarity Computation
- Principle:Protectai Modelscan Scan Configuration
- Principle:Sail sg LongSpec Tree Speculative Decoding
- Principle:FlagOpen FlagEmbedding Matryoshka Reranking
Implementations
- Implementation:Pyro ppl Pyro MixedHMM Model
- Implementation:Mlc ai Mlc llm Mistral Model
- Implementation:Microsoft Semantic kernel OpenAIPromptExecutionSettings
- Implementation:Langfuse Langfuse ObservationsTable Definition
- Implementation:Norrrrrrr lyn WAInjectBench SentenceTransformer Init
- Implementation:PeterL1n BackgroundMattingV2 MattingBase
- Implementation:Promptfoo Promptfoo CSV Parser
- Implementation:OpenGVLab InternVL Segmentation Transform Pipeline
- Implementation:Apache Kafka Git Branch And Tag Management
- Implementation:CrewAIInc CrewAI Agent Constructor For Specialists
Heuristics
- Heuristic:OpenGVLab InternVL Loss Reduction Strategy
- Heuristic:Microsoft DeepSpeedExamples LoRA Learning Rate Scaling
- Heuristic:NVIDIA NeMo Curator Video Frame Sampling Strategy
- Heuristic:Haotian liu LLaVA Tokenizer Version Offset Correction
- Heuristic:Spcl Graph of thoughts Budget Gated Benchmark Execution
- Heuristic:Marker Inc Korea AutoRAG Batch Size Tuning
- Heuristic:Facebookresearch Audiocraft Audio Normalization Strategies
- Heuristic:PrefectHQ Prefect SQLite Performance Tuning
- Heuristic:Microsoft Semantic kernel Experimental Feature Opt In
- Heuristic:BerriAI Litellm Streaming Loop Detection
Environments
- Environment:Treeverse LakeFS Go Runtime Environment
- Environment:Heibaiying BigData Notes Flink 1 9 Environment
- Environment:Kserve Kserve GPU Accelerator
- Environment:Helicone Helicone Node 20 TypeScript Runtime
- Environment:Cohere ai Cohere python AWS Integration Dependencies
- Environment:Deepset ai Haystack OpenAI API Environment
- Environment:Nightwatchjs Nightwatch Android Mobile Testing
- Environment:Protectai Modelscan H5py Optional
- Environment:Google research Deduplicate text datasets Rust Cargo Build Environment
- Environment:Axolotl ai cloud Axolotl Python Runtime