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:Spcl Graph of thoughts GoT Document Merging Pipeline
- Workflow:Apache Shardingsphere Cluster Mode Initialization
- Workflow:Webdriverio Webdriverio WDIO Testrunner Setup
- Workflow:Mlc ai Web llm Web Worker Deployment
- Workflow:Pytorch Serve HuggingFace Transformer Serving
- Workflow:Helicone Helicone LLM Response Normalization
- Workflow:Facebookresearch Habitat lab Agent Benchmarking
- Workflow:Openai Openai node Function Calling
- Workflow:Alibaba MNN Model Compression
- Workflow:Mlflow Mlflow GenAI Evaluation
Principles
- Principle:NVIDIA TransformerEngine FP8 Delayed Scaling
- Principle:Princeton nlp Tree of thought llm Experiment Configuration
- Principle:Online ml River Online ML Utilities
- Principle:Cleanlab Cleanlab Token Issue Display
- Principle:Anthropics Anthropic sdk python SDK Infrastructure
- Principle:Openai Openai agents python Guardrail Attachment
- Principle:Apache Kafka Cherry Pick Backport
- Principle:Helicone Helicone Query Filtering
- Principle:Heibaiying BigData Notes Flink Stream Transformations
- Principle:Langchain ai Langgraph Deprecation Management
Implementations
- Implementation:Kubeflow Pipelines Profile Controller Sync
- Implementation:Datajuicer Data juicer GenerateQAFromTextMapper Process
- Implementation:Scikit learn Scikit learn KernelPCA
- Implementation:Ucbepic Docetl APIKeysDialog
- Implementation:InternLM Lmdeploy Gemm Desc
- Implementation:BerriAI Litellm Agent Types
- Implementation:Langchain ai Langgraph BaseChannel
- Implementation:BerriAI Litellm MLflow Logger
- Implementation:InternLM Lmdeploy Core Mma
- Implementation:Online ml River Metrics MAE
Heuristics
- Heuristic:Apache Beam GC Thrashing Detection
- Heuristic:Spotify Luigi Batch Parameter Aggregation
- Heuristic:Mlflow Mlflow Prompt Cache Tuning
- Heuristic:OpenGVLab InternVL Gradient Checkpointing Memory
- Heuristic:Huggingface Peft LoRA Initialization Strategy Selection
- Heuristic:Infiniflow Ragflow Reranking Weight Tuning
- Heuristic:Duckdb Duckdb Unity Build Strategy
- Heuristic:Cypress io Cypress Xvfb Display Gotcha
- Heuristic:Huggingface Trl Disable Dropout For RL Training
- Heuristic:Huggingface Alignment handbook EOS Token Alignment
Environments
- Environment:Liu00222 Open Prompt Injection Python Dependencies
- Environment:Open compass VLMEvalKit Data Storage Environment
- Environment:Predibase Lorax CUDA GPU Runtime
- Environment:Langgenius Dify Node Frontend Environment
- Environment:Treeverse LakeFS Web UI Environment
- Environment:VainF Torch Pruning YOLO Pruning Dependencies
- Environment:Scikit learn Scikit learn OpenMP Thread Configuration
- Environment:Huggingface Diffusers Quantization Environment
- Environment:EvolvingLMMs Lab Lmms eval Python Runtime Environment
- Environment:Gretelai Gretel synthetics PyTorch CUDA Environment