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:Microsoft Semantic kernel Agent Conversation And Orchestration
- Workflow:Langgenius Dify Application Creation
- Workflow:Google research Deduplicate text datasets Cross dataset deduplication
- Workflow:Langchain ai Langchain Vector Store Operations
- Workflow:Huggingface Datatrove FineWeb Dataset Creation
- Workflow:ChenghaoMou Text dedup SimHash Deduplication
- Workflow:SqueezeAILab ETS ETS Experiment Pipeline
- Workflow:SeleniumHQ Selenium Selenium Grid Deployment
- Workflow:Volcengine Verl Vision Language Model RL Training
- Workflow:Intel Ipex llm vLLM Serving
Principles
- Principle:Testtimescaling Testtimescaling github io API Data Fetching
- Principle:Huggingface Transformers CI Notification And Reporting
- Principle:Apache Shardingsphere Runtime Rule Object Initialization
- Principle:Langchain ai Langchain Chat Model Initialization
- Principle:CrewAIInc CrewAI Output Processing
- Principle:Apache Flink PyFlink Build Distribution
- Principle:Confident ai Deepeval Installation and Configuration
- Principle:Huggingface Datatrove Core Data Structures
- Principle:Duckdb Duckdb Function Registration Generation
- Principle:Heibaiying BigData Notes Storm Spout Implementation
Implementations
- Implementation:Lance format Lance LegacyListEncoding
- Implementation:Alibaba MNN Diffusion HuggingFace Download
- Implementation:Openai Openai python Image Edit Completed Event
- Implementation:Alibaba MNN Protobuf Descriptor H
- Implementation:Kubeflow Pipelines Kubernetes PVC Sample
- Implementation:Iterative Dvc Testing Path Info
- Implementation:Tensorflow Tfjs Layer Utils
- Implementation:Openclaw Openclaw DashboardCommand
- Implementation:Openai Openai python Response Reasoning Item Param
- Implementation:Fede1024 Rust rdkafka Producer Transaction Methods
Heuristics
- Heuristic:Haotian liu LLaVA Use Cache Training Inference Toggle
- Heuristic:Microsoft Onnxruntime Flash Attention Optimization
- Heuristic:Eventual Inc Daft Delta Lake S3 Locking
- Heuristic:Huggingface Optimum Dummy Input Shape Defaults
- Heuristic:Pola rs Polars Collect All For Diverging Queries
- Heuristic:Apache Airflow Variable Access Pattern
- Heuristic:VainF Torch Pruning Pruning Ratio vs Parameter Ratio
- Heuristic:Microsoft BIPIA LLAMA Pad Token Workaround
- Heuristic:Sail sg LongSpec Tree Shape Configuration
- Heuristic:Huggingface Diffusers LoRA Safe Fusing
Environments
- Environment:Deepspeedai DeepSpeed XPU Environment
- Environment:FMInference FlexLLMGen HuggingFace Access
- Environment:Hiyouga LLaMA Factory FP8 Training Environment
- Environment:Treeverse LakeFS LakeFS Server Environment
- Environment:Protectai Modelscan TensorFlow Optional
- Environment:Triton inference server Server GPU CUDA Runtime
- Environment:Huggingface Transformers Python 310 Runtime
- Environment:Intel Ipex llm RAG LlamaIndex Environment
- Environment:Sgl project Sglang OpenAI
- Environment:Huggingface Alignment handbook Python Transformers