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:Ucbepic Docetl Long Document Chunking
- Workflow:Haotian liu LLaVA Single Image Inference
- Workflow:Promptfoo Promptfoo CI CD Integration
- Workflow:Dagster io Dagster DSPy Optimization
- Workflow:Eric mitchell Direct preference optimization Custom Dataset Integration
- Workflow:Kserve Kserve InferenceGraph Pipeline
- Workflow:Trailofbits Fickling PyTorch Format Identification
- Workflow:Deepset ai Haystack RAG Evaluation Pipeline
- Workflow:Nightwatchjs Nightwatch Cucumber BDD Integration
- Workflow:Facebookresearch Habitat lab PointNav PPO Training
Principles
- Principle:Triton inference server Server QA Shell Test Infrastructure
- Principle:ARISE Initiative Robosuite Controller Factory Pattern
- Principle:BerriAI Litellm API Key Management
- Principle:Google deepmind Mujoco BVH Acceleration
- Principle:Tencent Ncnn Bounding Box Decoding
- Principle:NVIDIA TransformerEngine Tensor Parallel Initialization
- Principle:Microsoft Onnxruntime Model Metadata Inspection
- Principle:Duckdb Duckdb Fast Number Parsing
- Principle:Microsoft Semantic kernel Conversation Thread Management
- Principle:Ggml org Llama cpp Ngram Speculative Drafting
Implementations
- Implementation:Predibase Lorax Metadata Kernels
- Implementation:Huggingface Datatrove SymbolLinesFormatter
- Implementation:Protectai Llm guard Relevance
- Implementation:Datajuicer Data juicer ExtractEntityAttributeMapper
- Implementation:Apache Druid Coordinator Dynamic Config Completions
- Implementation:Ggml org Llama cpp Json Schema To Grammar Header
- Implementation:Datahub project Datahub HdfsPathDataset
- Implementation:Fastai Fastbook Add Datepart
- Implementation:Googleapis Python genai AsyncLiveMusic Connect
- Implementation:Explodinggradients Ragas SemanticSimilarity Metric
Heuristics
- Heuristic:Tensorflow Serving Batching Thread Tuning
- Heuristic:Deepseek ai Janus Bfloat16 Dtype Selection
- Heuristic:Farama Foundation Gymnasium Sync Vs Async VectorEnv Selection
- Heuristic:Vibrantlabsai Ragas Warning Deprecated V1 Metrics
- Heuristic:Liu00222 Open Prompt Injection Cosine Similarity Segmentation Threshold
- Heuristic:Mbzuai oryx Awesome LLM Post training Depth Limit Recursion At 2
- Heuristic:Explodinggradients Ragas Deprecation Migration Guide
- Heuristic:Cypress io Cypress Browser Version Workarounds
- Heuristic:Facebookresearch Audiocraft Audio Normalization Strategies
- Heuristic:Run llama Llama index Finetuning Warmup Steps
Environments
- Environment:Eventual Inc Daft AI Provider Dependencies
- Environment:Allenai Open instruct Docker Container
- Environment:Datajuicer Data juicer LLM API Credentials Environment
- Environment:Alibaba MNN GPU Metal Environment
- Environment:Avdvg InjectGuard CUDA GPU
- Environment:Nautechsystems Nautilus trader Databento API Credentials
- Environment:Huggingface Optimum Python Core Dependencies
- Environment:HKUDS AI Trader Python LangChain Runtime
- Environment:Openai Openai python Azure OpenAI
- Environment:Huggingface Peft Python Core Dependencies