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:Allenai Open instruct DPO Preference Tuning
- Workflow:Googleapis Python genai Image Generation Pipeline
- Workflow:Googleapis Python genai Function Calling and Tools
- Workflow:Recommenders team Recommenders ALS Spark Recommendation
- Workflow:Allenai Open instruct GRPO Reinforcement Learning
- Workflow:Protectai Llm guard Scanner Benchmarking
- Workflow:OWASP Www project top 10 for large language model applications Vulnerability Entry Development
- Workflow:Alibaba MNN Python Model Inference
- Workflow:Mit han lab Llm awq HuggingFace Model Export
- Workflow:Apache Kafka Coordinator Runtime Lifecycle
Principles
- Principle:Helicone Helicone Marketing Attribution
- Principle:Mlflow Mlflow Protobuf Code Generation
- Principle:ARISE Initiative Robosuite MJCF Model Hierarchy
- Principle:Ollama Ollama GGUF Model Conversion Bert
- Principle:Unstructured IO Unstructured Section Aware Chunking
- Principle:PeterL1n BackgroundMattingV2 ONNX export
- Principle:Facebookresearch Habitat lab HRL Configuration Composition
- Principle:Haotian liu LLaVA Weight Delta Application
- Principle:ArroyoSystems Arroyo SQL Table Integration
- Principle:BerriAI Litellm Retry And Fallback
Implementations
- Implementation:Ray project Ray Buildkite Build Pipeline
- Implementation:BerriAI Litellm Fallback Utils
- Implementation:Tensorflow Serving Server BuildAndStart
- Implementation:Apache Spark Distribution Placement
- Implementation:Openai Openai node AzureOpenAI
- Implementation:SeleniumHQ Selenium Closure Testing Mock
- Implementation:Promptfoo Promptfoo Database Migration
- Implementation:Ggml org Llama cpp Android GgufMetadata
- Implementation:PeterL1n BackgroundMattingV2 Camera
- Implementation:Lance format Lance JNI FileReader
Heuristics
- Heuristic:Nightwatchjs Nightwatch Warning Deprecated API Members
- Heuristic:NVIDIA DALI NVJPEG Memory Preallocation
- Heuristic:Infiniflow Ragflow Embedding Batch Size Constraint
- Heuristic:Facebookresearch Habitat lab VER Tuning Guidelines
- Heuristic:Lucidrains X transformers Sampling Temperature Strategy
- Heuristic:Heibaiying BigData Notes HBase Connection Thread Safety Tip
- Heuristic:Apache Druid Auto Granularity Selection
- Heuristic:Bigscience workshop Petals KV Cache Sizing For Attention Types
- Heuristic:Microsoft BIPIA OpenAI Rate Limit Retry
- Heuristic:CarperAI Trlx Reward Model Layer Freezing
Environments
- Environment:Microsoft Agent framework Python 3 10 Runtime
- Environment:FlagOpen FlagEmbedding Finetuning Environment
- Environment:Openai Openai python Azure OpenAI
- Environment:Microsoft Onnxruntime Python Inference Environment
- Environment:ArroyoSystems Arroyo Object Storage
- Environment:Kserve Kserve Python Runtime
- Environment:Unslothai Unsloth CUDA VLLM
- Environment:Sgl project Sglang GitHub Actions
- Environment:Microsoft LoRA NLU Conda Environment
- Environment:Huggingface Transformers PEFT Adapter Env