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:Huggingface Transformers PEFT Adapter Integration
- Workflow:Sdv dev SDV Constrained synthesis
- Workflow:Openai Openai python Audio Processing
- Workflow:PrefectHQ Prefect Web Scraping Pipeline
- Workflow:Fede1024 Rust rdkafka At Least Once Processing
- Workflow:ARISE Initiative Robomimic Hyperparameter Sweep
- Workflow:Cleanlab Cleanlab Token Classification Label Quality
- Workflow:Romsto Speculative Decoding Ngram Assisted Speculative Decoding
- Workflow:Huggingface Peft Seq2Seq AdaLoRA Finetuning
- Workflow:Microsoft Onnxruntime Distributed Model Training
Principles
- Principle:Protectai Llm guard Toxicity Detection
- Principle:Huggingface Diffusers Quantized Model Loading
- Principle:Huggingface Datasets SQL Dataset Building
- Principle:Huggingface Datasets Hub Metadata Configs
- Principle:Langgenius Dify Annotation System
- Principle:Lm sys FastChat Condensed Rotary Embedding
- Principle:LaurentMazare Tch rs SGD Optimization
- Principle:Alibaba ROLL Diffusion Model Preparation
- Principle:Eric mitchell Direct preference optimization SFT Checkpoint Loading
- Principle:Cypress io Cypress Test Suite Execution
Implementations
- Implementation:Apache Dolphinscheduler DataSourceUtils Query
- Implementation:Ollama Ollama Imagegen ZImage Transformer
- Implementation:Open compass VLMEvalKit MathVista Utils
- Implementation:Deepspeedai DeepSpeed Evoformer MMA Accum Lambda
- Implementation:Pyro ppl Pyro GP TimeSeries
- Implementation:Ollama Ollama Llama Public API
- Implementation:CARLA simulator Carla BufferView
- Implementation:Ollama Ollama Tokenizer BPE
- Implementation:Duckdb Duckdb FastPForLib
- Implementation:Junyanz Pytorch CycleGAN and pix2pix Download Pretrained Model
Heuristics
- Heuristic:Microsoft LoRA Warning Deprecated Legacy Examples
- Heuristic:Langchain ai Langchain Deprecation Version Tracking
- Heuristic:Speechbrain Speechbrain Nonfinite Loss Handling
- Heuristic:Run llama Llama index Embedding Batch Size Tuning
- Heuristic:Huggingface Optimum Device Offload Constraints
- Heuristic:OWASP Www project top 10 for large language model applications Deliberately Insecure Code Isolation
- Heuristic:Triton inference server Server Documentation Standards
- Heuristic:Vibrantlabsai Ragas Warning Deprecated V1 Metrics
- Heuristic:Apache Kafka Log4j Migration Compatibility
- Heuristic:Iamhankai Forest of Thought Early Stop Majority Vote
Environments
- Environment:Microsoft DeepSpeedExamples VisualChat Training Environment
- Environment:Truera Trulens Streamlit Dashboard Environment
- Environment:Apache Flink Node Build Environment
- Environment:ARISE Initiative Robosuite GPU Rendering
- Environment:Diagram of thought Diagram of thought LLM API
- Environment:NVIDIA DALI CMake Build Environment
- Environment:Pyro ppl Pyro CUDA GPU Acceleration
- Environment:Sktime Pytorch forecasting Optuna Tuning Dependencies
- Environment:Apache Spark Python Environment
- Environment:Lance format Lance Rust Toolchain