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:Openai Whisper Word Level Timestamps
- Workflow:Langfuse Langfuse Otel ingestion pipeline
- Workflow:Pytorch Serve LLM Deployment vLLM
- Workflow:ClickHouse ClickHouse Contributing Pull Request
- Workflow:Haotian liu LLaVA Benchmark Evaluation
- Workflow:Huggingface Transformers PEFT Adapter Integration
- Workflow:LaurentMazare Tch rs MNIST Training
- Workflow:Axolotl ai cloud Axolotl Multimodal Vision Finetuning
- Workflow:ChenghaoMou Text dedup MinHash LSH Deduplication
- Workflow:BerriAI Litellm Router Load Balancing
Principles
- Principle:Huggingface Datatrove Symbol Line Removal
- Principle:Confident ai Deepeval Trace Configuration
- Principle:Ollama Ollama KVCache Composite Caching
- Principle:Datajuicer Data juicer Data Mapping Transformation
- Principle:DataTalksClub Data engineering zoomcamp Pipeline Cleanup
- Principle:Ucbepic Docetl Programmatic Optimization
- Principle:Protectai Llm guard Factual Consistency Checking
- Principle:Sdv dev SDV Range Constraint
- Principle:Tensorflow Serving HTTP Server Implementation
- Principle:Lm sys FastChat Prompt Deduplication
Implementations
- Implementation:Datajuicer Data juicer VideoHandReconstructionHaworMapper
- Implementation:Mlc ai Mlc llm Image Processing
- Implementation:Astronomer Astronomer cosmos Watcher Operators
- Implementation:Haosulab ManiSkill ANYmalC
- Implementation:Teamcapybara Capybara Chrome Node
- Implementation:Lm sys FastChat Split Train Test
- Implementation:Spotify Luigi Sphinx Doc Configuration
- Implementation:FlagOpen FlagEmbedding MLVU Choice Bench
- Implementation:CARLA simulator Carla WheelPhysicsControl
- Implementation:Openai Openai python Response Function Shell Tool Call
Heuristics
- Heuristic:Datahub project Datahub Secret Handling And Deprecation Patterns
- Heuristic:Teamcapybara Capybara Negative Predicate Matching
- Heuristic:Ollama Ollama Download Retry Strategy
- Heuristic:Guardrails ai Guardrails Async Vs Sync Validation Mode
- Heuristic:PacktPublishing LLM Engineers Handbook Dataset Generation Quality Filters
- Heuristic:Apache Druid Explore Compare Query Strategy
- Heuristic:Openclaw Openclaw WebSocket Reconnection And Session Cleanup
- Heuristic:Neuml Txtai Memory Streaming Optimization
- Heuristic:Spcl Graph of thoughts Four Bit Quantization For Local LLMs
- Heuristic:Fastai Fastbook Embedding Size Rule
Environments
- Environment:Explodinggradients Ragas Optional Metrics Environment
- Environment:Microsoft LoRA PyTorch CUDA Environment
- Environment:Ggml org Llama cpp CUDA GPU Environment
- Environment:CrewAIInc CrewAI Optional Provider Dependencies
- Environment:Intel Ipex llm Linux XPU Environment
- Environment:Langfuse Langfuse Docker Infrastructure
- Environment:Astronomer Astronomer cosmos Kubernetes Provider
- Environment:NVIDIA NeMo Curator Python Linux Base
- Environment:Huggingface Datasets SQL Dependencies
- Environment:Marker Inc Korea AutoRAG VLLM Environment