Main Page
27,667
Total Pages
1,118
Workflows
7,697
Principles
16,832
Implementations
1,245
Heuristics
909
Environments
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:Microsoft Agent framework Declarative Agent Definition
- Workflow:Mlc ai Web llm Text Embeddings And RAG
- Workflow:Run llama Llama index RAG Query Pipeline
- Workflow:Wandb Weave LLM Integration Tracing
- Workflow:Mlc ai Web llm Chrome Extension Integration
- Workflow:Openai Evals Building a custom eval
- Workflow:Explodinggradients Ragas LLM Benchmarking
- Workflow:Shiyu coder Kronos Single Series Prediction
- Workflow:TA Lib Ta lib python Basic Indicator Computation
- Workflow:Dotnet Machinelearning GenAI Causal LM Inference
Principles
- Principle:Arize ai Phoenix OTel Dependency Setup
- Principle:Triton inference server Server Ensemble Validation
- Principle:Dagster io Dagster Rate Limiting Strategy
- Principle:Volcengine Verl Multimodal Rollout Generation
- Principle:Ggml org Llama cpp Constrained Decoding
- Principle:FMInference FlexLLMGen Distributed Checkpoint Management
- Principle:ClickHouse ClickHouse Object Pooling
- Principle:Apache Paimon Utility Infrastructure
- Principle:SeldonIO Seldon core Experiment Lifecycle Management
- Principle:OpenGVLab InternVL Benchmark Dispatch
Implementations
- Implementation:Ucbepic Docetl Python API Schema Objects
- Implementation:Duckdb Duckdb Libpg Query Parser
- Implementation:Openai Whisper SubtitlesWriter Iterate Result
- Implementation:Google deepmind Mujoco CI Build Steps
- Implementation:Google deepmind Mujoco Filetype Detection
- Implementation:Huggingface Datatrove InferenceDatasetCardGenerator
- Implementation:Webdriverio Webdriverio ESLint NoPause
- Implementation:Ray project Ray Serve Shutdown
- Implementation:Facebookresearch Audiocraft RelativeVolumeMel
- Implementation:NVIDIA TransformerEngine JAX Flax Module
Heuristics
- Heuristic:Liu00222 Open Prompt Injection BPE Retokenization Parameters
- Heuristic:Langfuse Langfuse Eval Loop Prevention
- Heuristic:Datajuicer Data juicer Operator Fusion Rules
- Heuristic:Danijar Dreamerv3 Symlog TwoHot Prediction
- Heuristic:Fastai Fastbook Discriminative Learning Rates
- Heuristic:Datajuicer Data juicer Checkpoint Resumption Strategy
- Heuristic:NVIDIA NeMo Aligner PPO Critic Warmup Tip
- Heuristic:Bigscience workshop Petals KV Cache Sizing For Attention Types
- Heuristic:Avhz RustQuant MC Parallel Path Threshold
- Heuristic:TobikoData Sqlmesh Forward Only Safety
Environments
- Environment:Kubeflow Kubeflow Python KFP SDK Environment
- Environment:Roboflow Rf detr Python GPU Environment
- Environment:DataTalksClub Data engineering zoomcamp Dbt DuckDB Environment
- Environment:Fastai Fastbook Sklearn Environment
- Environment:FlowiseAI Flowise Database Environment
- Environment:Sgl project Sglang CUDA Runtime
- Environment:Dagster io Dagster GRPC Communication
- Environment:Vibrantlabsai Ragas Google Drive Backend Environment
- Environment:ClickHouse ClickHouse Python3 Test Environment
- Environment:Norrrrrrr lyn WAInjectBench External Repos Dependencies