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:InternLM Lmdeploy VLM Inference Pipeline
- Workflow:Openclaw Openclaw Multi Agent Routing
- Workflow:Vespa engine Vespa CI CD build pipeline
- Workflow:Duckdb Duckdb Code Generation Pipeline
- Workflow:Dotnet Machinelearning Binary Classification Pipeline
- Workflow:Obss Sahi COCO Evaluation
- Workflow:Facebookresearch Audiocraft EnCodec Compression Training
- Workflow:Neuml Txtai Pipeline Workflow Chaining
- Workflow:Protectai Modelscan Custom Scanner Plugin
- Workflow:Huggingface Datatrove FineWeb Dataset Creation
Principles
- Principle:Huggingface Peft SFT Training
- Principle:Getgauge Taiko Response Mocking
- Principle:Ggml org Llama cpp Server Configuration
- Principle:Infiniflow Ragflow Knowledge Base Creation
- Principle:Microsoft Onnxruntime Memory Optimization
- Principle:Recommenders team Recommenders Stratified Data Splitting
- Principle:Dotnet Machinelearning Segment Encoding Optimization
- Principle:Alibaba ROLL Rollout Scheduling
- Principle:Zai org CogVideo SAT YAML Configuration
- Principle:PacktPublishing LLM Engineers Handbook Pipeline Reporting
Implementations
- Implementation:Open compass VLMEvalKit Mantis
- Implementation:Vllm project Vllm Logprobs
- Implementation:Microsoft DeepSpeedExamples DeepSpeed Initialize CIFAR
- Implementation:Langchain ai Langchain VectorStore As Retriever
- Implementation:Huggingface Datasets Lance Builder
- Implementation:Datajuicer Data juicer CleanHtmlMapper
- Implementation:Microsoft Playwright FfNetworkManager
- Implementation:Lucidrains X transformers TransformerWrapper Decoder Init
- Implementation:Evidentlyai Evidently Legacy Trigger Words Feature
- Implementation:Online ml River Stats MAD
Heuristics
- Heuristic:Duckdb Duckdb Test Development Guidelines
- Heuristic:Unstructured IO Unstructured Hi Res Model Configuration
- Heuristic:Heibaiying BigData Notes Maven Shade Packaging Tip
- Heuristic:Teamcapybara Capybara Async Waiting And Retry
- Heuristic:Apache Beam Executor Shutdown Ordering
- Heuristic:Anthropics Anthropic sdk python Adaptive Thinking Over Enabled
- Heuristic:Tensorflow Tfjs GPU Pipeline Data Residency
- Heuristic:Roboflow Rf detr Small Dataset Oversampling
- Heuristic:AnswerDotAI RAGatouille Auto Batch Size For Long Documents
- Heuristic:PacktPublishing LLM Engineers Handbook Token Window Safety Margin
Environments
- Environment:Protectai Llm guard ONNX Runtime Acceleration
- Environment:TobikoData Sqlmesh BigQuery Connection
- Environment:Protectai Modelscan TensorFlow Optional
- Environment:FlagOpen FlagEmbedding Finetuning Environment
- Environment:Apache Dolphinscheduler Netty Runtime
- Environment:Lakeraai Pint benchmark Python 310 With Transformers
- Environment:Vespa engine Vespa CMake Cpp23 Build Environment
- Environment:Intel Ipex llm XPU Inference Environment
- Environment:Heibaiying BigData Notes Flink 1 9 Environment
- Environment:Microsoft DeepSpeedExamples SuperOffload Runtime