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:Avhz RustQuant Stochastic Process Simulation
- Workflow:MarketSquare Robotframework browser Plugin Development
- Workflow:AUTOMATIC1111 Stable diffusion webui Textual inversion training
- Workflow:Openai Evals Running a single eval
- Workflow:Deepseek ai Janus Autoregressive Image Generation
- Workflow:Huggingface Diffusers Checkpoint Conversion
- Workflow:Apache Flink Stream File Compaction
- Workflow:Bitsandbytes foundation Bitsandbytes 8bit LLM Int8 Inference
- Workflow:Microsoft Autogen Swarm Agent Handoff
- Workflow:Vespa engine Vespa Linguistics text processing pipeline
Principles
- Principle:Huggingface Datatrove Language Filtering
- Principle:Mlflow Mlflow Error Handling and Exception Hierarchy
- Principle:Microsoft Semantic kernel Conversation Thread Management
- Principle:Scikit learn Scikit learn Probability Calibration
- Principle:CrewAIInc CrewAI Crew Assembly
- Principle:ArroyoSystems Arroyo Checkpoint Triggering
- Principle:Vespa engine Vespa FRT Transport and Failover
- Principle:Truera Trulens Custom App Wrapping
- Principle:Neuml Txtai Training Data Preparation
- Principle:Mit han lab Llm awq NVILA Multimodal Architecture
Implementations
- Implementation:SeldonIO Seldon core Seldon Model Load
- Implementation:Explodinggradients Ragas Discrete Metric Decorator
- Implementation:Lm sys FastChat Clean Chat Data
- Implementation:Microsoft Semantic kernel SignalR GenerateDocumentsChat
- Implementation:Kserve Kserve LLMInferenceService Full CRD
- Implementation:Microsoft Semantic kernel KernelProcessStep
- Implementation:Langchain ai Langchain FastEmbedSparse
- Implementation:Apache Flink SingletonResultIterator
- Implementation:Vllm project Vllm Spec Decode Method Config
- Implementation:Kubeflow Pipelines Kustomize Build Apply
Heuristics
- Heuristic:Openai Whisper Median Word Duration Clamping
- Heuristic:Langgenius Dify Workflow Draft Hash Sync
- Heuristic:Togethercomputer Together python Fine Tuning Parameter Validation
- Heuristic:Princeton nlp SimPO BOS Token Handling
- Heuristic:Heibaiying BigData Notes HBase Connection Thread Safety Tip
- Heuristic:Fastai Fastbook Progressive Resizing
- Heuristic:PrefectHQ Prefect Retry Backoff Strategy
- Heuristic:Huggingface Open r1 Test Batch Early Termination
- Heuristic:Lm sys FastChat Tokenizer Offset Correction
- Heuristic:Facebookresearch Audiocraft Chroma Conditioning Cache Requirement
Environments
- Environment:Microsoft LoRA PyTorch CUDA Environment
- Environment:Spotify Luigi Apache Spark
- Environment:Scikit learn Scikit learn Python Runtime Environment
- Environment:Duckdb Duckdb CMake Build Toolchain
- Environment:Marker Inc Korea AutoRAG Python 3 10 Runtime
- Environment:Huggingface Datasets Lance Dependencies
- Environment:Duckdb Duckdb Code Formatting Tools
- Environment:Marker Inc Korea AutoRAG Vector Database Backends
- Environment:Heibaiying BigData Notes Hadoop CDH Environment
- Environment:Vllm project Vllm Benchmarks