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:Langchain ai Langchain Adding Partner Integration
- Workflow:NVIDIA TransformerEngine FP8 Training Quickstart
- Workflow:Bigscience workshop Petals Prompt Tuning Classification
- Workflow:PrefectHQ Prefect Per Worker Task Concurrency
- Workflow:Open compass VLMEvalKit Image Benchmark Evaluation
- Workflow:Scikit learn contrib Imbalanced learn Balanced Deep Learning Training
- Workflow:Groq Groq python Text Embedding
- Workflow:Langgenius Dify RAG Pipeline Development
- Workflow:Huggingface Datasets Dataset Streaming
- Workflow:Huggingface Datatrove FineWeb Dataset Creation
Principles
- Principle:Marker Inc Korea AutoRAG Strategy Selection
- Principle:FlagOpen FlagEmbedding Embedding Similarity Computation
- Principle:SeleniumHQ Selenium Code Formatting Pipeline
- Principle:Sktime Pytorch forecasting TimeXer Architecture
- Principle:Microsoft DeepSpeedExamples Inference Performance Measurement
- Principle:Diagram of thought Diagram of thought Final Synthesis
- Principle:SeleniumHQ Selenium Bazel Build Verification
- Principle:Tencent Ncnn Neural Network Inference
- Principle:Microsoft Agent framework Magentic Orchestration Pattern
- Principle:Huggingface Open r1 Training Callbacks
Implementations
- Implementation:Confident ai Deepeval Update Current Span
- Implementation:Risingwavelabs Risingwave MySqlOffsetContext
- Implementation:Haotian liu LLaVA Predictor Class
- Implementation:Evidentlyai Evidently Legacy Text Part Feature
- Implementation:Neuml Txtai SBert Vectors
- Implementation:Treeverse LakeFS Java SDK Model ObjectStats
- Implementation:Microsoft Playwright PageAgentDispatcher
- Implementation:Microsoft DeepSpeedExamples PreLN Bert LayerDrop Modeling
- Implementation:Getgauge Taiko Highlight
- Implementation:NVIDIA DALI EfficientNet Common Blocks
Heuristics
- Heuristic:VainF Torch Pruning AutoGrad Dependency Graph
- Heuristic:Testtimescaling Testtimescaling github io Dual JSON Sync
- Heuristic:Microsoft LoRA Scaling Factor Alpha Over R
- Heuristic:FMInference FlexLLMGen Sequence Length Alignment
- Heuristic:Huggingface Datasets Batch Size Optimization
- Heuristic:Fede1024 Rust rdkafka Sensitive Config Sanitization
- Heuristic:MarketSquare Robotframework browser GRPC Response Chunking
- Heuristic:Openai Openai agents python Sensitive Data Logging Defaults
- Heuristic:EvolvingLMMs Lab Lmms eval Limit Flag Testing Only
- Heuristic:Vllm project Vllm Attention Backend Selection
Environments
- Environment:Microsoft Onnxruntime Distributed Training Environment
- Environment:Helicone Helicone Node 20 TypeScript Runtime
- Environment:Obss Sahi Python Pycocotools
- Environment:Openai Openai python Realtime WebSocket
- Environment:Openclaw Openclaw State Directory And Credentials
- Environment:Mlfoundations Open flamingo WebDataset Training Dependencies
- Environment:Google deepmind Dm control OSMesa Software Rendering
- Environment:PacktPublishing LLM Engineers Handbook Python 3 11 Poetry Environment
- Environment:Google deepmind Mujoco MJX JAX Environment
- Environment:Openai Openai python Voice Helpers