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:Vibrantlabsai Ragas Prompt Optimization
- Workflow:Huggingface Alignment handbook QLoRA Single GPU Finetuning
- Workflow:Explodinggradients Ragas LLM Benchmarking
- Workflow:Openai Openai agents python Streaming Agent Execution
- Workflow:Apache Flink File Source Pipeline
- Workflow:Apache Hudi Docker Demo Setup
- Workflow:Open compass VLMEvalKit API Model Evaluation
- Workflow:Mit han lab Llm awq AWQ Model Quantization
- Workflow:Bentoml BentoML Multi Model Composition
- Workflow:Openai Openai python Image Generation
Principles
- Principle:Arize ai Phoenix Annotation Querying
- Principle:Ollama Ollama ToolCalling
- Principle:LaurentMazare Tch rs Weight Loading
- Principle:Triton inference server Server Multi Server Deployment
- Principle:Lm sys FastChat Train Test Data Splitting
- Principle:Kubeflow Kubeflow Community Engagement
- Principle:Truera Trulens Session Initialization
- Principle:Dotnet Machinelearning Fast Fourier Transform
- Principle:Online ml River Imbalanced Learning
- Principle:Iterative Dvc Data Index Update
Implementations
- Implementation:Trailofbits Fickling Find File Properties
- Implementation:ARISE Initiative Robosuite Wrapper Base
- Implementation:Microsoft Playwright Generate Injected
- Implementation:Vllm project Vllm CPU Attn NEON
- Implementation:Langchain ai Langgraph RemoteGraph Init
- Implementation:AUTOMATIC1111 Stable diffusion webui UI Settings
- Implementation:Mage ai Mage ai Google Sheets Transform
- Implementation:Speechbrain Speechbrain GigaSpeech Dataset
- Implementation:CARLA simulator Carla VehiclePIDController Run Step
- Implementation:BerriAI Litellm Cache Init
Heuristics
- Heuristic:TobikoData Sqlmesh Snapshot TTL Defaults
- Heuristic:Online ml River SNARIMAX Default Regressor Pipeline
- Heuristic:Mit han lab Llm awq Skip QK Projection Clipping
- Heuristic:OpenGVLab InternVL Dynamic Resolution Tiling
- Heuristic:Langchain ai Langgraph Stream Mode Selection
- Heuristic:Zai org CogVideo Memory Optimization Strategies
- Heuristic:Protectai Llm guard PyTorch Compile Warmup
- Heuristic:Sdv dev SDV HMA Schema Simplification
- Heuristic:Spotify Luigi Marker Table Idempotency
- Heuristic:Vespa engine Vespa Config Polling Timeout Tuning
Environments
- Environment:Pytorch Serve vLLM Engine Environment
- Environment:Microsoft Playwright Browser Binaries Environment
- Environment:Shiyu coder Kronos PyTorch CUDA Environment
- Environment:Snorkel team Snorkel SpaCy NLP
- Environment:Deepspeedai DeepSpeed Python Runtime Environment
- Environment:ClickHouse ClickHouse OpenSSL Runtime
- Environment:OpenHands OpenHands Third Party Runtime Credentials
- Environment:Infiniflow Ragflow Python Runtime
- Environment:Wandb Weave LLM Integration Dependencies
- Environment:Google deepmind Dm control Python MuJoCo Runtime