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:Explodinggradients Ragas Metric Prompt Optimization
- Workflow:Dotnet Machinelearning AutoML Experiment
- Workflow:ContextualAI HALOs Offline SFT Alignment Pipeline
- Workflow:Sgl project Sglang Frontend Language Multi Turn Chat
- Workflow:Mlfoundations Open flamingo Distributed Training
- Workflow:MarketSquare Robotframework browser Plugin Development
- Workflow:Cleanlab Cleanlab CleanLearning Robust Training
- Workflow:Duckdb Duckdb Code Generation Pipeline
- Workflow:Lucidrains X transformers Non Autoregressive Masked Generation
- Workflow:Apache Spark Kubernetes Deployment
Principles
- Principle:Mistralai Client python Finetuning Job Monitoring
- Principle:Allenai Open instruct Reward Model Initialization
- Principle:ARISE Initiative Robosuite MJCF Model Hierarchy
- Principle:Alibaba ROLL Video Generation and Reward
- Principle:Ollama Ollama Adapter Conversion
- Principle:Fede1024 Rust rdkafka Concurrent Worker Scaling
- Principle:Openai Openai python Audio Playback
- Principle:Lm sys FastChat MT Bench Answer Generation
- Principle:Mit han lab Llm awq AWQ HuggingFace Export
- Principle:Langchain ai Langgraph Graph Module Definition
Implementations
- Implementation:FlagOpen FlagEmbedding BGE Coder TripletGenerator
- Implementation:Groq Groq python Embedding Input Pattern
- Implementation:Ggml org Llama cpp Grammar
- Implementation:Apache Paimon BTreeFileFooter
- Implementation:Openai Openai python Response Compaction Item
- Implementation:Explodinggradients Ragas StringMetrics Module
- Implementation:NVIDIA NeMo Curator CommonCrawlDownloadExtractStage
- Implementation:Tensorflow Serving Resnet K8s Manifest
- Implementation:Neuml Txtai RetrieveTask
- Implementation:Online ml River Forest ARFClassifier
Heuristics
- Heuristic:Alibaba ROLL PPO Clipping Defaults
- Heuristic:Junyanz Pytorch CycleGAN and pix2pix High Res Crop Training
- Heuristic:Anthropics Anthropic sdk python Adaptive Thinking Over Enabled
- Heuristic:Huggingface Open r1 Code Execution Timeout Strategy
- Heuristic:Junyanz Pytorch CycleGAN and pix2pix CuDNN Benchmark Scale Width
- Heuristic:CrewAIInc CrewAI MCP Timeout And Retry Strategy
- Heuristic:Deepseek ai Janus Bfloat16 Dtype Selection
- Heuristic:Haosulab ManiSkill GPU Memory Buffer Tuning
- Heuristic:Onnx Onnx Protobuf 2GB Limit Workaround
- Heuristic:Bigscience workshop Petals KV Cache Sizing For Attention Types
Environments
- Environment:Spcl Graph of thoughts OpenAI API Access
- Environment:Huggingface Trl PEFT LoRA Environment
- Environment:Pytorch Serve Distributed Training Environment
- Environment:Princeton nlp SimPO VLLM Inference
- Environment:Predibase Lorax Model Source Credentials
- Environment:Vllm project Vllm Python Dependencies
- Environment:Huggingface Trl vLLM Generation Environment
- Environment:Avhz RustQuant Rust Stable
- Environment:Apache Druid Druid Operator Kubernetes
- Environment:Pola rs Polars Rust Build Environment