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:Interpretml Interpret EBM Model Export
- Workflow:Shiyu coder Kronos Single Series Prediction
- Workflow:Trailofbits Fickling Safe ML Model Loading
- Workflow:FMInference FlexLLMGen Text Completion API
- Workflow:ContextualAI HALOs Model Evaluation
- Workflow:Recommenders team Recommenders Neural Collaborative Filtering
- Workflow:Puppeteer Puppeteer PDF Generation
- Workflow:PacktPublishing LLM Engineers Handbook LLM Finetuning
- Workflow:Deepset ai Haystack Hybrid Document Search
- Workflow:Getgauge Taiko Headless Browser Testing
Principles
- Principle:Tencent Ncnn Vulkan GPU Detection
- Principle:Huggingface Datatrove HTTP Media Fetching
- Principle:ClickHouse ClickHouse RAII Scope Guard
- Principle:Turboderp org Exllamav2 Model Configuration
- Principle:Helicone Helicone ClickHouse Cost SQL Generation
- Principle:Interpretml Interpret Synthetic Data
- Principle:Pola rs Polars Rust Crate Feature System
- Principle:Apache Hudi Clustering Strategy Configuration
- Principle:Apache Beam Windmill Connection Setup
- Principle:Mlc ai Mlc llm Preemption Recovery
Implementations
- Implementation:Helicone Helicone Ch Hcone Migrate
- Implementation:Sgl project Sglang Attention Ops
- Implementation:Ggml org Ggml Gpt tokenize
- Implementation:Marker Inc Korea AutoRAG Make Basic Gen Gt
- Implementation:Openai Evals AnthropicSolver
- Implementation:Infiniflow Ragflow Collapse Component
- Implementation:Facebookresearch Habitat lab GuiThrowHelper
- Implementation:Pytorch Serve Metrics API
- Implementation:Datajuicer Data juicer ImageRemoveBackgroundMapper
- Implementation:Vibrantlabsai Ragas EvaluationDataset From List
Heuristics
- Heuristic:Princeton nlp SimPO Dropout Disabling
- Heuristic:Datahub project Datahub Secret Handling And Deprecation Patterns
- Heuristic:TA Lib Ta lib python Compatibility Mode Switching
- Heuristic:Tencent Ncnn Optimize Before Quantize
- Heuristic:TA Lib Ta lib python Unstable Period Configuration
- Heuristic:Tencent Ncnn Vulkan Pipeline Warmup
- Heuristic:Huggingface Datasets Batch Size Optimization
- Heuristic:Mlc ai Web llm Grammar Matcher Reuse
- Heuristic:Microsoft LoRA LoRA Rank Selection
- Heuristic:Deepseek ai Janus Bfloat16 Operation Workarounds
Environments
- Environment:Open compass VLMEvalKit GPU CUDA Environment
- Environment:Rapidsai Cuml CUDA GPU
- Environment:Mlflow Mlflow Python Runtime Environment
- Environment:Cohere ai Cohere python Python SDK Runtime
- Environment:Microsoft Playwright Platform Support Environment
- Environment:Farama Foundation Gymnasium Python 3 10 Runtime
- Environment:Bentoml BentoML BentoCloud Credentials
- Environment:NVIDIA TransformerEngine Python PyTorch Requirements
- Environment:Treeverse LakeFS LakeFS Server Environment
- Environment:Vllm project Vllm Distributed