Main Page
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:Zai org CogVideo Diffusers LoRA Finetuning
- Workflow:SeleniumHQ Selenium Page Object Pattern Testing
- Workflow:Ollama Ollama Safetensors To GGUF Conversion
- Workflow:Unslothai Unsloth GRPO Reinforcement Learning
- Workflow:ThreeSR Awesome Inference Time Scaling Automated Paper Addition
- Workflow:Mlc ai Web llm Function Calling
- Workflow:Ggml org Llama cpp Multimodal Inference
- Workflow:MaterializeInc Materialize CI Pipeline Generation
- Workflow:Onnx Onnx External Data Handling
- Workflow:Ucbepic Docetl Playground Interactive Development
Principles
- Principle:Mit han lab Llm awq Per Channel Scaling Search
- Principle:Openai Evals Completion Function Resolution
- Principle:Mlflow Mlflow ML Framework Compatibility Management
- Principle:Mistralai Client python Chat Completion
- Principle:Ucbepic Docetl Deterministic Code Operations
- Principle:TA Lib Ta lib python Installation Verification
- Principle:Cleanlab Cleanlab Coteaching Algorithm
- Principle:Online ml River Online Nearest Neighbors
- Principle:DataTalksClub Data engineering zoomcamp Chunked Data Ingestion
- Principle:CrewAIInc CrewAI Semantic Retrieval
Implementations
- Implementation:Kubeflow Pipelines Dsl Component Decorator
- Implementation:Googleapis Python genai Common Utilities
- Implementation:CARLA simulator Carla RPC Server
- Implementation:Lance format Lance LanceDataFrame
- Implementation:CARLA simulator Carla TrafficManager Configuration
- Implementation:Tensorflow Serving Tfrt Classifier Test
- Implementation:Duckdb Duckdb Mbedtls Hash
- Implementation:Pyro ppl Pyro SVI Step
- Implementation:Kserve Kserve MLServer Runtime
- Implementation:Neuml Txtai API Create
Heuristics
- Heuristic:Anthropics Anthropic sdk python Warning Deprecated LegacyAPIResponse
- Heuristic:Turboderp org Exllamav2 Quantization Conversion Tips
- Heuristic:Langfuse Langfuse ClickHouse FINAL Skip Optimization
- Heuristic:Promptfoo Promptfoo WAL Mode Network Filesystem
- Heuristic:Gretelai Gretel synthetics Batch Size Divisibility Constraints
- Heuristic:Mlc ai Web llm KV Cache Window Configuration
- Heuristic:Helicone Helicone Cost Precision Multiplier
- Heuristic:Promptfoo Promptfoo Retry With Jitter
- Heuristic:Alibaba ROLL GPU Memory Offload Strategy
- Heuristic:Huggingface Diffusers LoRA Safe Fusing
Environments
- Environment:LLMBook zh LLMBook zh github io Bitsandbytes Quantization Environment
- Environment:AnswerDotAI RAGatouille Python ColBERT Dependencies
- Environment:Dotnet Machinelearning OneDal Acceleration
- Environment:Deepset ai Haystack HuggingFace Model Environment
- Environment:Apache Shardingsphere Etcd Cluster Coordination
- Environment:Sktime Pytorch forecasting Cpflows MQF2 Dependencies
- Environment:Huggingface Peft BitsAndBytes Quantization
- Environment:ArroyoSystems Arroyo Kubernetes Deployment
- Environment:Avdvg InjectGuard CUDA GPU
- Environment:MaterializeInc Materialize Kubernetes Helm Runtime