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:Vibrantlabsai Ragas Custom Metric Creation
- Workflow:Haifengl Smile SQL Analytics Pipeline
- Workflow:Eventual Inc Daft SQL Query Analytics
- Workflow:OpenHands OpenHands Third Party Runtime Integration
- Workflow:Openclaw Openclaw Multi Agent Routing
- Workflow:Risingwavelabs Risingwave CDC Data Replication
- Workflow:Puppeteer Puppeteer Web Scraping And Interaction
- Workflow:Ggml org Llama cpp HF to GGUF Model Conversion
- Workflow:Ucbepic Docetl Pipeline Optimization
- Workflow:Iterative Dvc Pipeline Reproduction
Principles
- Principle:Protectai Llm guard Scanner Benchmarking
- Principle:Neuml Txtai Production Deployment
- Principle:Ggml org Llama cpp DiffusionGeneration
- Principle:PrefectHQ Prefect HTML Fetching
- Principle:Ggml org Llama cpp Structured Output
- Principle:NVIDIA NeMo Curator Fuzzy Duplicate Identification
- Principle:Datajuicer Data juicer Configuration Initialization
- Principle:Huggingface Datasets Python Utilities
- Principle:Microsoft Semantic kernel RAG Chat Augmentation
- Principle:Ggml org Ggml Vectorized Math Operations
Implementations
- Implementation:Lance format Lance Java JniLoader
- Implementation:FMInference FlexLLMGen DistOptLM
- Implementation:Pyro ppl Pyro PyroModule Class
- Implementation:Hpcaitech ColossalAI RetrievalConversation
- Implementation:Ollama Ollama Readline Buffer
- Implementation:Avhz RustQuant MertonJumpDiffusion Process
- Implementation:Risingwavelabs Risingwave PgOutputMessageDecoder
- Implementation:OpenGVLab InternVL Segmentation Test
- Implementation:Run llama Llama index LabelledRagDataset
- Implementation:Kornia Kornia Mutual Information Loss
Heuristics
- Heuristic:Huggingface Alignment handbook QLoRA Learning Rate Scaling
- Heuristic:Anthropics Anthropic sdk python Model Deprecation Awareness
- Heuristic:Interpretml Interpret EBM Hyperparameter Tuning Guide
- Heuristic:OpenGVLab InternVL Dynamic Resolution Tiling
- Heuristic:Pyro ppl Pyro MCMC Warmup Adaptation
- Heuristic:Danijar Dreamerv3 XLA GPU Optimization Flags
- Heuristic:Dagster io Dagster Lazy Import Pattern
- Heuristic:HKUDS AI Trader Linear Retry Backoff
- Heuristic:Rapidsai Cuml CUDA Kernel Caching
- Heuristic:NVIDIA NeMo Aligner Higher Stability Log Probs
Environments
- Environment:Bigscience workshop Petals Python Hivemind
- Environment:Pyro ppl Pyro Distributed Training
- Environment:Kserve Kserve Gateway API
- Environment:Mbzuai oryx Awesome LLM Post training Git CLI
- Environment:Dotnet Machinelearning Native Build Toolchain
- Environment:Ollama Ollama Go Runtime
- Environment:Haosulab ManiSkill GPU CUDA Simulation
- Environment:Arize ai Phoenix Phoenix Server Runtime
- Environment:Openclaw Openclaw Node 22 Runtime
- Environment:Apache Kafka Release Toolchain Environment