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:Ray project Ray Serve Deployment
- Workflow:Vllm project Vllm Multi LoRA Serving
- Workflow:Avhz RustQuant Stochastic Process Simulation
- Workflow:Predibase Lorax Structured JSON Output
- Workflow:Lm sys FastChat LoRA QLoRA Finetuning
- Workflow:Neuml Txtai Pipeline Workflow Chaining
- Workflow:Tensorflow Serving Model Version Management
- Workflow:Sail sg LongSpec Long Context Evaluation
- Workflow:Openclaw Openclaw Multi Agent Routing
- Workflow:LMCache LMCache Disaggregated Prefill
Principles
- Principle:LLMBook zh LLMBook zh github io Symmetric Quantization
- Principle:Mbzuai oryx Awesome LLM Post training Progressive Data Checkpointing
- Principle:Gretelai Gretel synthetics Tokenizer Training
- Principle:Deepset ai Haystack Retrieval MRR Evaluation
- Principle:Ggml org Llama cpp HashingUtilities
- Principle:Volcengine Verl Parquet Export
- Principle:Dotnet Machinelearning Segment Encoding Optimization
- Principle:Microsoft Onnxruntime Memory Optimization
- Principle:Openclaw Openclaw Container Storage Configuration
- Principle:Zai org CogVideo Autoencoder Architecture
Implementations
- Implementation:MarketSquare Robotframework browser Initialize Js Extension
- Implementation:Hpcaitech ColossalAI Eval BaseDataset
- Implementation:Marker Inc Korea AutoRAG Random Single Hop
- Implementation:Truera Trulens Selector Init
- Implementation:Mlc ai Mlc llm Function Table
- Implementation:Kornia Kornia Inlier Mask Indexing
- Implementation:SeldonIO Seldon core Seldon Pipeline Status
- Implementation:ARISE Initiative Robosuite TiagoRobot
- Implementation:Hiyouga LLaMA Factory DPO Zh Demo Data
- Implementation:CrewAIInc CrewAI Bedrock Browser Toolkit
Heuristics
- Heuristic:Alibaba ROLL Dynamic Batching Token Limits
- Heuristic:Avdvg InjectGuard Embedding Normalization Cosine Equivalence
- Heuristic:ThreeSR Awesome Inference Time Scaling API Rate Limiting Tip
- Heuristic:Sail sg LongSpec Tree Shape Configuration
- Heuristic:Tensorflow Tfjs GPU Pipeline Data Residency
- Heuristic:ChenghaoMou Text dedup False Positive Verification Tradeoff
- Heuristic:Sktime Pytorch forecasting Encoder Decoder Length Limits
- Heuristic:Sdv dev SDV Sampling Retry Tuning
- Heuristic:Interpretml Interpret Memory Budget Heuristic
- Heuristic:Deepseek ai Janus CFG Weight Tuning
Environments
- Environment:Explodinggradients Ragas Python Runtime Environment
- Environment:Lakeraai Pint benchmark Python 310 With Pandas
- Environment:Pola rs Polars Cloud Storage Environment
- Environment:Intel Ipex llm NPU Environment
- Environment:Iterative Dvc Git SCM Environment
- Environment:Neuml Txtai GPU Accelerator Detection
- Environment:Obss Sahi Python Detection Frameworks
- Environment:Vllm project Vllm CUDA Runtime
- Environment:Allenai Open instruct CUDA GPU Training
- Environment:Microsoft LoRA NLG Eval External Tools