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:ChenghaoMou Text dedup Bloom Filter Deduplication
- Workflow:Nightwatchjs Nightwatch Page Object Pattern
- Workflow:Unslothai Unsloth QLoRA SFT Finetuning
- Workflow:Apache Spark Kubernetes Deployment
- Workflow:Neuml Txtai RAG Pipeline
- Workflow:PrefectHQ Prefect Per Worker Task Concurrency
- Workflow:Langchain ai Langchain Adding Partner Integration
- Workflow:ARISE Initiative Robosuite Gymnasium RL Integration
- Workflow:Puppeteer Puppeteer Browser Installation And Management
- Workflow:Mbzuai oryx Awesome LLM Post training Deep Paper Collection
Principles
- Principle:LLMBook zh LLMBook zh github io Quality Filtering
- Principle:Fede1024 Rust rdkafka Topic Subscription And Consumption
- Principle:Ggml org Ggml Hexagon DSP Computation
- Principle:CARLA simulator Carla Simulation Recording
- Principle:Confident ai Deepeval Agent Entry Point Definition
- Principle:Speechbrain Speechbrain Noisy Speech Data Preparation
- Principle:Interpretml Interpret Linear Model Explanation
- Principle:Ggml org Llama cpp State Serialization
- Principle:Huggingface Diffusers Quantized Model Saving
- Principle:OWASP Www project top 10 for large language model applications Real World Incident Cross Reference
Implementations
- Implementation:Online ml River Imblearn RandomSampler
- Implementation:Kubeflow Pipelines Metacontroller CRD
- Implementation:Alibaba MNN Protobuf Map Field H
- Implementation:Apache Airflow Lifecycle Listener Spec
- Implementation:Sgl project Sglang Sgl Function Run
- Implementation:Bentoml BentoML DeploymentConfigParameters
- Implementation:Marker Inc Korea AutoRAG Api Runner Run Api Server
- Implementation:Openai Openai python Response MCP Call Args Done
- Implementation:BerriAI Litellm Responses Utils
- Implementation:Treeverse LakeFS Java SDK Model Commit
Heuristics
- Heuristic:Norrrrrrr lyn WAInjectBench Balanced Class Weights Imbalanced Data
- Heuristic:Huggingface Trl Distributed Device Map Override
- Heuristic:Openai Whisper No Speech Detection
- Heuristic:Elevenlabs Elevenlabs python TTS Model Selection
- Heuristic:Microsoft Onnxruntime Convergence Debugging Tips
- Heuristic:Rapidsai Cuml Float64 Kernel Stability
- Heuristic:Apache Spark Memory Tuning Tips
- Heuristic:Ggml org Ggml Sampling Parameter Defaults
- Heuristic:DevExpress Testcafe MacOS Browser Launch Serialization
- Heuristic:NVIDIA NeMo Curator Semantic Dedup Cluster Sizing
Environments
- Environment:AnswerDotAI RAGatouille Python ColBERT Dependencies
- Environment:Intel Ipex llm XPU Inference Environment
- Environment:Pyro ppl Pyro Visualization Tools
- Environment:Explodinggradients Ragas Optional Metrics Environment
- Environment:OpenBMB UltraFeedback HuggingFace Hub Environment
- Environment:Marker Inc Korea AutoRAG Korean NLP Dependencies
- Environment:Protectai Modelscan TensorFlow Optional
- Environment:Iamhankai Forest of Thought Python CUDA Runtime
- Environment:Isaac sim IsaacGymEnvs Pip Dependencies
- Environment:OpenHands OpenHands Frontend Build Environment