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:Sail sg LongSpec Long Context Evaluation
- Workflow:Google deepmind Mujoco Offscreen video recording
- Workflow:DataTalksClub Data engineering zoomcamp Docker PostgreSQL Data Ingestion
- Workflow:Kserve Kserve Canary Rollout Deployment
- Workflow:Trailofbits Fickling PyTorch Payload Injection
- Workflow:Online ml River Binary Classification Pipeline
- Workflow:Alibaba MNN Stable Diffusion Deployment
- Workflow:Princeton nlp SimPO SimPO Training
- Workflow:Mlfoundations Open flamingo Distributed Training
- Workflow:FlagOpen FlagEmbedding Embedder Inference
Principles
- Principle:Arize ai Phoenix Experiment Task Definition
- Principle:Microsoft Playwright Test File Creation
- Principle:DistrictDataLabs Yellowbrick Knee Point Detection
- Principle:Sgl project Sglang Generation Output Processing
- Principle:Nightwatchjs Nightwatch Page Object Usage In Tests
- Principle:Deepset ai Haystack Document Embedding
- Principle:PacktPublishing LLM Engineers Handbook Document Cleaning
- Principle:DataTalksClub Data engineering zoomcamp Merge Upsert
- Principle:Datahub project Datahub Deployment Verification
- Principle:Microsoft Semantic kernel Agent Process Integration
Implementations
- Implementation:Ggml org Llama cpp Ggml Backend Load All
- Implementation:Langchain ai Langgraph Init Chat Model
- Implementation:Allenai Open instruct Human Eval App
- Implementation:Apache Shardingsphere DataSourceUnitPersistService Persist
- Implementation:EvolvingLMMs Lab Lmms eval Create Iterator
- Implementation:Online ml River Compose TargetTransformRegressor
- Implementation:FMInference FlexLLMGen Transformers Setup
- Implementation:LLMBook zh LLMBook zh github io LlamaRMSNorm
- Implementation:DevExpress Testcafe TestRunTracker
- Implementation:Ggml org Ggml Cpu kleidiai backend
Heuristics
- Heuristic:Roboflow Rf detr EMA Best Checkpoint Strategy
- Heuristic:Scikit learn contrib Imbalanced learn KNeighbors Selection Tips
- Heuristic:Deepset ai Haystack Embedding Batch Size And Prefix
- Heuristic:Ollama Ollama Multimodal Parallel Restriction
- Heuristic:ContextualAI HALOs Online Round Budgeting
- Heuristic:Astronomer Astronomer cosmos Dbt Invocation Mode Selection
- Heuristic:Vibrantlabsai Ragas Warning Deprecated Legacy LLM Wrappers
- Heuristic:Anthropics Anthropic sdk python Warning Deprecated LegacyAPIResponse
- Heuristic:Elevenlabs Elevenlabs python Text Chunking Splitter Characters
- Heuristic:PrefectHQ Prefect SQLite Performance Tuning
Environments
- Environment:Scikit learn Scikit learn Python Runtime Environment
- Environment:Ggml org Llama cpp Vulkan GPU Environment
- Environment:DistrictDataLabs Yellowbrick Python Scikit Learn Environment
- Environment:Fastai Fastbook CUDA GPU Environment
- Environment:PacktPublishing LLM Engineers Handbook VLLM Evaluation Environment
- Environment:Googleapis Python genai Vertex AI Service Account
- Environment:Huggingface Alignment handbook Python Datasets
- Environment:Infiniflow Ragflow Python Runtime
- Environment:Datahub project Datahub Docker Runtime
- Environment:Intel Ipex llm NPU Environment