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:Huggingface Optimum Accelerated Inference Pipeline
- Workflow:Neuml Txtai RAG Pipeline
- Workflow:Pytorch Serve Large Model Inference
- Workflow:HKUDS AI Trader Data Pipeline
- Workflow:Truera Trulens RAG Evaluation With LangChain
- Workflow:Apache Kafka Release Candidate Staging
- Workflow:Cohere ai Cohere python Tool Use Agentic Chat
- Workflow:NVIDIA TransformerEngine Accelerate HF Llama With TE
- Workflow:Spcl Graph of thoughts GoT Keyword Counting Pipeline
- Workflow:Pola rs Polars Streaming Large Dataset Processing
Principles
- Principle:LaurentMazare Tch rs Seq2Seq Attention Translation
- Principle:Ggml org Llama cpp Server Build
- Principle:Huggingface Transformers Distributed Checkpointing
- Principle:ClickHouse ClickHouse Package Validation
- Principle:Tensorflow Tfjs Model Evaluation
- Principle:Haosulab ManiSkill Demonstration Data Acquisition
- Principle:Kubeflow Kubeflow Community Engagement
- Principle:Googleapis Python genai Response Processing
- Principle:Unstructured IO Unstructured Chunk Size Configuration
- Principle:Bigscience workshop Petals Health Monitoring
Implementations
- Implementation:Unstructured IO Unstructured Example Docs Fixture
- Implementation:Langgenius Dify UsePublishWorkflow
- Implementation:Evidentlyai Evidently Legacy Sentence Count Feature
- Implementation:Langchain ai Langchain Pyproject Toml Configuration
- Implementation:CrewAIInc CrewAI Firecrawl Scrape Tool
- Implementation:Ggml org Ggml Cpu x86 cpu feats
- Implementation:Apache Paimon ManifestFileManager
- Implementation:Facebookresearch Habitat lab HabitatEnvFactory
- Implementation:Tencent Ncnn SCRFD CrowdHuman Example
- Implementation:Ggml org Llama cpp Llama Get Embeddings
Heuristics
- Heuristic:Dagster io Dagster Retry Strategy Configuration
- Heuristic:Datahub project Datahub Secret Handling And Deprecation Patterns
- Heuristic:Openai Whisper No Speech Detection
- Heuristic:Microsoft Semantic kernel Prompt Injection Safety
- Heuristic:Infiniflow Ragflow Agent Max Rounds Strategy
- Heuristic:Astronomer Astronomer cosmos Dbt Invocation Mode Selection
- Heuristic:Mlc ai Mlc llm BLAS Dispatch Decision
- Heuristic:Apache Spark Memory Tuning Tips
- Heuristic:Confident ai Deepeval Dotenv Loading Order
- Heuristic:Groq Groq python Streaming Usage Stats
Environments
- Environment:Allenai Open instruct Beaker Cluster
- Environment:Sgl project Sglang CUDA GPU Runtime
- Environment:Huggingface Peft Optional Quantization Backends
- Environment:Pytorch Serve vLLM Engine Environment
- Environment:Infiniflow Ragflow Frontend Node Environment
- Environment:Marker Inc Korea AutoRAG VLLM Environment
- Environment:Microsoft Onnxruntime Sklearn Conversion Environment
- Environment:Openai Openai agents python MCP Dependencies
- Environment:FlagOpen FlagEmbedding Python PyTorch Environment
- Environment:Neuml Txtai GPU Accelerator Detection