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 Trl PPO RLHF Training
- Workflow:Mistralai Client python Text Embeddings
- Workflow:DistrictDataLabs Yellowbrick Cluster Analysis
- Workflow:Ucbepic Docetl Long Document Chunking
- Workflow:Kserve Kserve InferenceGraph Pipeline
- Workflow:Mit han lab Llm awq AWQ Model Quantization
- Workflow:NVIDIA NeMo Aligner DPO Training
- Workflow:Predibase Lorax Structured JSON Output
- Workflow:Mistralai Client python Azure Chat Completion
- Workflow:Alibaba ROLL Reward Flow Diffusion Pipeline
Principles
- Principle:Ggml org Llama cpp Speculation Initialization
- Principle:Zai org CogVideo Laplacian Pyramid Loss
- Principle:AUTOMATIC1111 Stable diffusion webui Model Identification
- Principle:Guardrails ai Guardrails Custom Validator Integration
- Principle:Microsoft Semantic kernel Kernel Builder Initialization
- Principle:Cleanlab Cleanlab Clean Model Inference
- Principle:Duckdb Duckdb Settings And Storage Info Generation
- Principle:Ray project Ray Runtime Shutdown
- Principle:HKUDS AI Trader JSONL Data Merging
- Principle:Spotify Luigi Hive Data Access
Implementations
- Implementation:OpenHands OpenHands DeviceCodeStore
- Implementation:Volcengine Verl Initialize Tools From Config
- Implementation:Huggingface Peft HRAModel
- Implementation:Elevenlabs Elevenlabs python WorkflowExpressionConditionModelOutputExpression
- Implementation:Microsoft Onnxruntime CUDA TrainingSplit
- Implementation:Farama Foundation Gymnasium NormalizeReward
- Implementation:Eventual Inc Daft Regexp Extract
- Implementation:Microsoft DeepSpeedExamples Add Argument CIFAR
- Implementation:Ray project Ray Sphinx Callouts Extension
- Implementation:Dotnet Machinelearning LdaModelBlock
Heuristics
- Heuristic:Avhz RustQuant MC Parallel Path Threshold
- Heuristic:Openai Openai agents python GPT 5 Reasoning Settings
- Heuristic:Gretelai Gretel synthetics Gumbel Softmax NaN Retry
- Heuristic:Groq Groq python Error Handling Hierarchy
- Heuristic:Openai Whisper No Speech Detection
- Heuristic:Huggingface Transformers Mixed Precision Training Selection
- Heuristic:Microsoft Onnxruntime ORTModule Wrapping Order
- Heuristic:Puppeteer Puppeteer Timeout Hierarchy
- Heuristic:Webdriverio Webdriverio Default Timeout Configuration
- Heuristic:Openai Openai python Structured Output Strict Schema
Environments
- Environment:Langchain ai Langgraph Postgres Checkpoint Environment
- Environment:Pytorch Serve DeepSpeed Environment
- Environment:Dotnet Machinelearning Dotnet SDK And Runtime
- Environment:Risingwavelabs Risingwave Rust Build Environment
- Environment:Huggingface Open r1 Slurm Cluster
- Environment:Deepspeedai DeepSpeed NVMe Environment
- Environment:Unstructured IO Unstructured Profiling Tools
- Environment:Teamcapybara Capybara Ruby And Gem Dependencies
- Environment:Marker Inc Korea AutoRAG GPU PyTorch Environment
- Environment:Allenai Open instruct Docker Container