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:Mlfoundations Open flamingo Few Shot Evaluation
- Workflow:Microsoft Playwright Network mocking and interception
- Workflow:Ggml org Ggml Backend Accelerated Computation
- Workflow:OpenBMB UltraFeedback GPT4 Preference Annotation
- Workflow:Lance format Lance Dataset Lifecycle
- Workflow:Groq Groq python Text Embedding
- Workflow:NVIDIA DALI Image Preprocessing Pipeline
- Workflow:Recommenders team Recommenders Neural Collaborative Filtering
- Workflow:Haotian liu LLaVA Single Image Inference
- Workflow:Norrrrrrr lyn WAInjectBench Text Prompt Injection Detection
Principles
- Principle:Sdv dev SDV Multi Table Data Sampling
- Principle:AUTOMATIC1111 Stable diffusion webui Latent Diffusion Pipeline
- Principle:Mlflow Mlflow Prediction Endpoint
- Principle:OpenHands OpenHands Post Migration Verification
- Principle:Tensorflow Serving Servable Access Pattern
- Principle:Unslothai Unsloth Supervised Finetuning
- Principle:AUTOMATIC1111 Stable diffusion webui Task Serialization
- Principle:Microsoft Agent framework Agent Context Management
- Principle:CARLA simulator Carla Sensor Data Processing
- Principle:Arize ai Phoenix OTel Dependency Setup
Implementations
- Implementation:ARISE Initiative Robosuite SimpleGripController
- Implementation:CrewAIInc CrewAI Crew Query Knowledge
- Implementation:Infiniflow Ragflow SetMetaDialog Component
- Implementation:Tensorflow Tfjs GPT2CausalLM Constructor
- Implementation:Infiniflow Ragflow Rag Tokenizer Tokenize
- Implementation:Online ml River Datasets Keystroke
- Implementation:Online ml River Optim Averager
- Implementation:Apache Druid Website Redirects
- Implementation:Infiniflow Ragflow FilesTable Component
- Implementation:Explodinggradients Ragas FewShotPydanticPrompt Class
Heuristics
- Heuristic:Marker Inc Korea AutoRAG Module Selection Strategies
- Heuristic:Googleapis Python genai LRO Polling Backoff
- Heuristic:Tensorflow Serving Batching Thread Tuning
- Heuristic:Teamcapybara Capybara Negative Predicate Matching
- Heuristic:Pola rs Polars Avoid Lambda In Aggregation
- Heuristic:FMInference FlexLLMGen Sequence Length Alignment
- Heuristic:Apache Druid Sampler Limitations And Workarounds
- Heuristic:AnswerDotAI RAGatouille In Memory Reranking Limits
- Heuristic:Scikit learn Scikit learn Random State Management
- Heuristic:Volcengine Verl GPU Memory Utilization Tuning
Environments
- Environment:FlowiseAI Flowise Database Environment
- Environment:Googleapis Python genai Vertex AI Service Account
- Environment:Huggingface Datatrove Python Runtime
- Environment:Testtimescaling Testtimescaling github io GitHub Actions Runner
- Environment:Pytorch Serve Distributed Training Environment
- Environment:ArroyoSystems Arroyo Rust Runtime
- Environment:Microsoft Semantic kernel ONNX CUDA Environment
- Environment:Rapidsai Cuml Dask Distributed
- Environment:Pola rs Polars Rust Build Environment
- Environment:Vllm project Vllm CUDA GPU Runtime