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:Datahub project Datahub Metadata Actions Pipeline
- Workflow:EvolvingLMMs Lab Lmms eval Custom Model Integration
- Workflow:Deepset ai Haystack Extractive QA Pipeline
- Workflow:Neuml Txtai Semantic Search
- Workflow:ChenghaoMou Text dedup MinHash LSH Deduplication
- Workflow:Shiyu coder Kronos CSV Finetuning
- Workflow:Spcl Graph of thoughts GoT Keyword Counting Pipeline
- Workflow:Turboderp org Exllamav2 EXL2 Model Conversion
- Workflow:DataTalksClub Data engineering zoomcamp dbt Analytics Transformation
- Workflow:ThreeSR Awesome Inference Time Scaling Manual Paper Contribution
Principles
- Principle:Ucbepic Docetl Pipeline Export
- Principle:Alibaba ROLL LLM Response Generation
- Principle:Norrrrrrr lyn WAInjectBench Text Embedding Initialization
- Principle:OpenHands OpenHands Business Route Mounting
- Principle:Vllm project Vllm Output Validation
- Principle:Nautechsystems Nautilus trader Python Package Configuration
- Principle:Mlc ai Mlc llm Prefill Decode Disaggregation
- Principle:Promptfoo Promptfoo Vulnerability Grading
- Principle:PacktPublishing LLM Engineers Handbook Vector Similarity Search
- Principle:Ggml org Ggml Model Architecture Initialization
Implementations
- Implementation:Microsoft Onnxruntime CPU CrossEntropy
- Implementation:Interpretml Interpret Harmonize Tensor
- Implementation:Huggingface Optimum MergeLinears
- Implementation:ClickHouse ClickHouse Wide Integer Impl
- Implementation:SeleniumHQ Selenium Bootstrap Main Entry
- Implementation:Protectai Llm guard Input InvisibleText
- Implementation:Cypress io Cypress AddTestingTypeToCypressConfig
- Implementation:Microsoft Semantic kernel KernelProcessStep
- Implementation:Turboderp org Exllamav2 TPContext
- Implementation:OpenRLHF OpenRLHF PolicyLoss
Heuristics
- Heuristic:Haotian liu LLaVA Image Aspect Ratio Padding Strategy
- Heuristic:Helicone Helicone Tiered Pricing Threshold Matching
- Heuristic:Arize ai Phoenix Warning Deprecated HallucinationEvaluator
- Heuristic:Ggml org Llama cpp Batch Size BLAS Minimum
- Heuristic:Kserve Kserve NCCL RoCE Auto Detection
- Heuristic:Facebookresearch Audiocraft Gradient Balancing For Multi Loss
- Heuristic:Iamhankai Forest of Thought UCB Exploration Constant
- Heuristic:Onnx Onnx Opset Version Selection
- Heuristic:Axolotl ai cloud Axolotl Memory Optimization Tips
- Heuristic:Triton inference server Server Documentation Standards
Environments
- Environment:Lm sys FastChat LoRA QLoRA Training Environment
- Environment:Fastai Fastbook CUDA GPU Environment
- Environment:Togethercomputer Together python API Credentials
- Environment:Mage ai Mage ai Singer SDK And Joblib Runtime
- Environment:Sgl project Sglang Distributed
- Environment:Facebookresearch Habitat lab HITL Runtime Environment
- Environment:FlowiseAI Flowise Docker Environment
- Environment:Microsoft LoRA PyTorch CUDA Environment
- Environment:Interpretml Interpret Native Libebm Environment
- Environment:Vllm project Vllm AMD ROCm