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:SeldonIO Seldon core Model Deployment
- Workflow:Groq Groq python Streaming Chat Completion
- Workflow:Ggml org Llama cpp Text Generation
- Workflow:Facebookresearch Habitat lab Custom Task Extension
- Workflow:Spotify Luigi Local Batch Pipeline
- Workflow:Kserve Kserve LLM Inference Serving
- Workflow:Puppeteer Puppeteer Request Interception
- Workflow:Tencent Ncnn Post Training Quantization
- Workflow:Vllm project Vllm Offline Text Generation
- Workflow:Vllm project Vllm OpenAI Compatible Serving
Principles
- Principle:Anthropics Anthropic sdk python SDK Infrastructure
- Principle:NVIDIA TransformerEngine Baseline Transformer Layer
- Principle:Langchain ai Langgraph Store Batch Operations
- Principle:Ggml org Ggml Training Data Loading
- Principle:Princeton nlp Tree of thought llm Thought Evaluation
- Principle:OpenGVLab InternVL DPO Data Collation
- Principle:ArroyoSystems Arroyo Pipeline Creation
- Principle:Langgenius Dify OAuthCallbackHandling
- Principle:Google research Deduplicate text datasets Self Similar Duplicate Detection
- Principle:Protectai Llm guard Vault State Management
Implementations
- Implementation:DataExpert io Data engineer handbook Log aggregation
- Implementation:Triton inference server Server SphinxDocConf
- Implementation:Huggingface Datasets Datasets CLI
- Implementation:Infiniflow Ragflow DocumentService Run
- Implementation:Online ml River Datasets TREC07
- Implementation:Apache Paimon JsonUtil
- Implementation:Trailofbits Fickling Interpreter To Ast
- Implementation:Kornia Kornia Mean Average Precision
- Implementation:Sgl project Sglang Kernel Utils Header
- Implementation:Fastai Fastbook Waterfall Ensemble
Heuristics
- Heuristic:PrefectHQ Prefect SQLite Performance Tuning
- Heuristic:Isaac sim IsaacGymEnvs Factory Velocity Limits
- Heuristic:DataTalksClub Data engineering zoomcamp GCS Upload Timeout Workaround
- Heuristic:Langchain ai Langgraph Retry Policy Configuration
- Heuristic:Facebookresearch Habitat lab VER Tuning Guidelines
- Heuristic:Huggingface Alignment handbook LoRA Rank Selection
- Heuristic:PrefectHQ Prefect Task Timeout Thread Limitation
- Heuristic:Apache Shardingsphere Version Cleanup After Switch
- Heuristic:Apache Paimon Compression Tuning
- Heuristic:Diagram of thought Diagram of thought Acyclicity Constraint Enforcement
Environments
- Environment:Sgl project Sglang Kubernetes
- Environment:LaurentMazare Tch rs Libtorch Build Environment
- Environment:Getgauge Taiko Chromium Browser
- Environment:Ggml org Llama cpp Metal GPU Environment
- Environment:Google deepmind Mujoco C Build Environment
- Environment:Vllm project Vllm ROCm
- Environment:Microsoft Playwright Browser Binaries Environment
- Environment:Microsoft Onnxruntime Sklearn Conversion Environment
- Environment:FlowiseAI Flowise Queue Mode Environment
- Environment:Pyro ppl Pyro CUDA GPU Acceleration