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:Turboderp org Exllamav2 Text Generation
- Workflow:Farama Foundation Gymnasium RL Agent Training Loop
- Workflow:Microsoft Semantic kernel Kernel Setup And Chat Completion
- Workflow:FlagOpen FlagEmbedding Benchmark Evaluation
- Workflow:OpenRLHF OpenRLHF Knowledge Distillation
- Workflow:Ggml org Ggml Model Conversion And Quantization
- Workflow:OpenGVLab InternVL Preference Optimization
- Workflow:Helicone Helicone Cost Calculation Pipeline
- Workflow:Alibaba ROLL DPO Training Pipeline
- Workflow:Openai Openai node Realtime Conversation
Principles
- Principle:Google deepmind Dm control MJCF Structure Building
- Principle:Microsoft Semantic kernel Process Step Definition
- Principle:Apache Kafka JMH Benchmark Execution
- Principle:VainF Torch Pruning LLM Config Update
- Principle:PrefectHQ Prefect HTTP Data Extraction
- Principle:Online ml River Probabilistic Data Structures
- Principle:Roboflow Rf detr Training Loop Execution
- Principle:Spcl Graph of thoughts Thought Aggregation
- Principle:DistrictDataLabs Yellowbrick PCA Projection
- Principle:Tensorflow Serving Serving Utilities
Implementations
- Implementation:Openai Openai node Uploads Resource
- Implementation:Microsoft Autogen Studio Sidebar
- Implementation:CrewAIInc CrewAI Website Search Tool
- Implementation:Google deepmind Mujoco API References Header
- Implementation:Risingwavelabs Risingwave JNI Binding Header
- Implementation:NVIDIA TransformerEngine Attention Backends
- Implementation:Microsoft Playwright Client EventEmitter
- Implementation:NVIDIA TransformerEngine Debug Per Tensor Scaling
- Implementation:Google deepmind Mujoco Filament GUI View
- Implementation:Tensorflow Serving Resource Util Test
Heuristics
- Heuristic:Risingwavelabs Risingwave Source Backoff Strategy
- Heuristic:ARISE Initiative Robomimic Rollout Horizon Selection
- Heuristic:Mlfoundations Open flamingo Gradient Clipping Max Norm
- Heuristic:CrewAIInc CrewAI RAG Search Defaults
- Heuristic:Langchain ai Langchain Text Splitter Separator Hierarchy
- Heuristic:CARLA simulator Carla PID Controller Tuning
- Heuristic:DataExpert io Data engineer handbook SparkSession Singleton Pattern
- Heuristic:Apache Spark Build Fallback Strategies
- Heuristic:Predibase Lorax GPU Sampling Optimization
- Heuristic:OpenRLHF OpenRLHF Gradient Checkpointing Memory Tip
Environments
- Environment:AnswerDotAI RAGatouille GPU CUDA Runtime
- Environment:Ggml org Llama cpp Vulkan GPU Environment
- Environment:Evidentlyai Evidently LLM Evaluation Environment
- Environment:Tensorflow Serving Docker Runtime Environment
- Environment:Unslothai Unsloth CUDA VLLM
- Environment:Lance format Lance Cloud Storage Credentials
- Environment:Microsoft LoRA NLG Eval External Tools
- Environment:SeldonIO Seldon core Kafka Messaging Environment
- Environment:Ray project Ray Java Build Environment
- Environment:Neuml Txtai GPU Accelerator Detection