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:Ucbepic Docetl Playground Interactive Development
- Workflow:Vibrantlabsai Ragas Custom Metric Creation
- Workflow:OpenGVLab InternVL LoRA Finetuning
- Workflow:Webdriverio Webdriverio Page Object Pattern
- Workflow:Mlc ai Web llm Function Calling
- Workflow:LLMBook zh LLMBook zh github io Supervised Finetuning
- Workflow:Open compass VLMEvalKit API Model Evaluation
- Workflow:Mbzuai oryx Awesome LLM Post training Awesome List Curation
- Workflow:Microsoft Semantic kernel Process Orchestration
- Workflow:CrewAIInc CrewAI Knowledge RAG Pipeline
Principles
- Principle:Rapidsai Cuml Incremental Learning
- Principle:NVIDIA DALI Pipeline Definition
- Principle:Huggingface Datasets Dataset Split Inspection
- Principle:Neuml Txtai API Security
- Principle:Apache Airflow Callback Event Notification
- Principle:AUTOMATIC1111 Stable diffusion webui Resource Monitoring
- Principle:Alibaba ROLL Knowledge Distillation Loss
- Principle:Fede1024 Rust rdkafka Manual Offset Management
- Principle:Bentoml BentoML Bento Building
- Principle:Ggml org Ggml Image IO
Implementations
- Implementation:Lance format Lance SessionCaches
- Implementation:NVIDIA NeMo Curator SemanticDeduplicationStage
- Implementation:Kornia Kornia SSIM Metric
- Implementation:Alibaba MNN Diffusion HuggingFace Download
- Implementation:ClickHouse ClickHouse Poco HTTPCookie
- Implementation:Gretelai Gretel synthetics TensorFlowConfig
- Implementation:Hpcaitech ColossalAI Train RM Script
- Implementation:Microsoft DeepSpeedExamples GLUE Classifier BERT Large
- Implementation:Online ml River Proba Beta
- Implementation:MarketSquare Robotframework browser Go To Click Fill Text
Heuristics
- Heuristic:Lm sys FastChat Greedy Decoding Temperature Threshold
- Heuristic:Protectai Modelscan Exit Code Conventions
- Heuristic:Google research Deduplicate text datasets HACKSIZE Overlap Buffer
- Heuristic:CrewAIInc CrewAI Rate Limiting Strategy
- Heuristic:Scikit learn contrib Imbalanced learn Sampling Strategy Selection
- Heuristic:Allenai Open instruct NCCL CUMEM Disable
- Heuristic:LLMBook zh LLMBook zh github io Greedy Decoding Temperature Zero
- Heuristic:Openai Whisper No Speech Detection
- Heuristic:Bentoml BentoML Warning Deprecated Legacy Service
- Heuristic:NVIDIA DALI NVJPEG Memory Preallocation
Environments
- Environment:Roboflow Rf detr Python GPU Environment
- Environment:Google research Deduplicate text datasets Python HuggingFace Environment
- Environment:Apache Druid Druid Operator Kubernetes
- Environment:Roboflow Rf detr Roboflow Deployment Credentials
- Environment:Kubeflow Kubeflow Git GitHub Environment
- Environment:SqueezeAILab ETS Evaluation Python Stack
- Environment:Heibaiying BigData Notes Flink 1 9 Environment
- Environment:Facebookresearch Audiocraft FAD TensorFlow Environment
- Environment:SeleniumHQ Selenium Contributor Development Environment
- Environment:Teamcapybara Capybara Selenium WebDriver Environment