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:AUTOMATIC1111 Stable diffusion webui Hypernetwork training
- Workflow:OpenHands OpenHands GitHub Webhook Event Processing
- Workflow:InternLM Lmdeploy W4A16 AWQ Quantization
- Workflow:Neuml Txtai Semantic Search Pipeline
- Workflow:MarketSquare Robotframework browser JavaScript Extension
- Workflow:SeldonIO Seldon core Model Explainability
- Workflow:Recommenders team Recommenders Algorithm Benchmarking
- Workflow:Haotian liu LLaVA Two Stage Pretraining and Finetuning
- Workflow:Protectai Llm guard Scanner Benchmarking
- Workflow:Eric mitchell Direct preference optimization DPO Preference Training
Principles
- Principle:Deepset ai Haystack LLM Chat Generation
- Principle:Explodinggradients Ragas Multi Turn Evaluation Schema
- Principle:Astronomer Astronomer cosmos Local Operator Execution
- Principle:Sktime Pytorch forecasting TFT V2 Architecture
- Principle:OpenGVLab InternVL LLaVA Multimodal Architecture
- Principle:Tensorflow Tfjs Convolutional Neural Networks
- Principle:Marker Inc Korea AutoRAG Corpus Instantiation
- Principle:Pyro ppl Pyro Epidemiological Modeling
- Principle:Helicone Helicone Application Services
- Principle:Ggml org Llama cpp Distributed Inference
Implementations
- Implementation:Ollama Ollama Llama Chat
- Implementation:InternLM Lmdeploy Impl 16816
- Implementation:Kubeflow Pipelines Cache Key Protobuf
- Implementation:Ollama Ollama Tools Template
- Implementation:Apache Kafka Gradle Maven Publish
- Implementation:Vibrantlabsai Ragas Core Utility Functions
- Implementation:NVIDIA TransformerEngine Debug Disable Quant GEMM
- Implementation:Facebookresearch Audiocraft GeneralUtils
- Implementation:CrewAIInc CrewAI Directory Search Tool
- Implementation:DevExpress Testcafe BrowserProviderPluginHost
Heuristics
- Heuristic:LMCache LMCache Prefix Based Retrieval Pattern
- Heuristic:Huggingface Optimum Dummy Input Shape Defaults
- Heuristic:Langchain ai Langgraph Durability Mode Selection
- Heuristic:Langgenius Dify Credential Sanitization In API Responses
- Heuristic:Norrrrrrr lyn WAInjectBench L2 Normalize CLIP Embeddings
- Heuristic:Explodinggradients Ragas Embedding Batch Size Tuning
- Heuristic:CarperAI Trlx KL Coefficient Adaptation
- Heuristic:Sktime Pytorch forecasting Target Normalization Transforms
- Heuristic:Google deepmind Mujoco Solver Selection Guide
- Heuristic:Datahub project Datahub Spark Databricks Coalescing
Environments
- Environment:Intel Ipex llm Windows Environment
- Environment:Huggingface Peft Python Core Dependencies
- Environment:Ollama Ollama CGo Runtime
- Environment:Langchain ai Langchain Unit Test Network Isolation
- Environment:Treeverse LakeFS LakeFS Server Environment
- Environment:Wandb Weave Python SDK Runtime
- Environment:Bentoml BentoML BentoCloud Credentials
- Environment:BerriAI Litellm Redis Cache Backend
- Environment:Turboderp org Exllamav2 CUDA GPU Runtime
- Environment:TA Lib Ta lib python Python Build Environment