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:Mit han lab Llm awq AWQ Model Evaluation
- Workflow:Deepspeedai DeepSpeed Sequence Parallel Long Context Training
- Workflow:Protectai Llm guard PII Anonymization Deanonymization
- Workflow:Haosulab ManiSkill RL Training with PPO
- Workflow:Getgauge Taiko Form Interaction Testing
- Workflow:SeldonIO Seldon core Model Explainability
- Workflow:Mlfoundations Open flamingo Model Creation And Inference
- Workflow:Princeton nlp SimPO Model Inference
- Workflow:Confident ai Deepeval Synthetic Dataset Generation
- Workflow:Turboderp org Exllamav2 Text Generation
Principles
- Principle:Run llama Llama index Pipeline Execution
- Principle:Spotify Luigi Hive Data Access
- Principle:Openclaw Openclaw Documentation Site Configuration
- Principle:Vllm project Vllm Output Processing
- Principle:Explodinggradients Ragas Framework Message Conversion
- Principle:ClickHouse ClickHouse SIMD Character Search
- Principle:ARISE Initiative Robosuite Rendering Abstraction
- Principle:Apache Hudi Schema Compatibility Verification
- Principle:Infiniflow Ragflow Chunk Filtering
- Principle:Huggingface Peft Adapter Injection
Implementations
- Implementation:Pyro ppl Pyro Poutine Handlers
- Implementation:Puppeteer Puppeteer TestServer
- Implementation:Kserve Kserve IAP Request Auth
- Implementation:Confident ai Deepeval Evaluate Trace
- Implementation:Mage ai Mage ai Docs Site Configuration
- Implementation:Online ml River Tree Splitter Gaussian
- Implementation:Lucidrains X transformers Paired Sequence Generator Pattern
- Implementation:Avhz RustQuant Utils
- Implementation:Lance format Lance Java SQBuildParams
- Implementation:Openai Openai python Container Retrieve Response
Heuristics
- Heuristic:Apache Dolphinscheduler HikariCP Pool Tuning
- Heuristic:Interpretml Interpret EBM Hyperparameter Tuning Guide
- Heuristic:Shiyu coder Kronos Sampling Temperature Tuning
- Heuristic:Eventual Inc Daft Execution Config Tuning
- Heuristic:Vibrantlabsai Ragas Nest Asyncio Uvloop Compatibility
- Heuristic:Apache Airflow Task Dependency Isolation
- Heuristic:Cleanlab Cleanlab Multiprocessing Platform Strategy
- Heuristic:NVIDIA NeMo Curator Video Frame Sampling Strategy
- Heuristic:Cypress io Cypress Browser Version Workarounds
- Heuristic:OWASP Www project top 10 for large language model applications SHA Pinning For GitHub Actions
Environments
- Environment:Isaac sim IsaacGymEnvs Pip Dependencies
- Environment:Vllm project Vllm CUDA Hopper
- Environment:Huggingface Diffusers Quantization Environment
- Environment:Datajuicer Data juicer LLM API Credentials Environment
- Environment:PrefectHQ Prefect AI Integration Credentials
- Environment:Huggingface Optimum Accelerated Inference Environment
- Environment:Tencent Ncnn PyTorch Environment
- Environment:AUTOMATIC1111 Stable diffusion webui GPU Compute Backend
- Environment:Huggingface Transformers 3D Parallel Multi GPU
- Environment:NVIDIA DALI CUDA GPU Environment