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:Heibaiying BigData Notes Spark SQL Data Analysis
- Workflow:Deepset ai Haystack RAG Pipeline
- Workflow:Langchain ai Langgraph Human in the Loop Agent
- Workflow:Romsto Speculative Decoding Interactive CLI Comparison
- Workflow:Apache Hudi Docker Demo Setup
- Workflow:Ray project Ray Cross Language Invocation
- Workflow:Isaac sim IsaacGymEnvs RL Policy Training
- Workflow:Explodinggradients Ragas LLM Benchmarking
- Workflow:Pola rs Polars Streaming Large Dataset Processing
- Workflow:Googleapis Python genai Model Fine Tuning
Principles
- Principle:Treeverse LakeFS Java SDK Client Configuration
- Principle:Mlflow Mlflow Evaluation Dataset Preparation
- Principle:Togethercomputer Together python Model Listing
- Principle:Kubeflow Kubeflow Feature Development Tracking
- Principle:Microsoft LoRA LoRA Checkpoint Evaluation
- Principle:LaurentMazare Tch rs REINFORCE Policy Gradient
- Principle:Deepset ai Haystack LLM Chat Generation
- Principle:Ggml org Llama cpp Computation Graph Building
- Principle:Huggingface Diffusers Diffusion Training Loop
- Principle:Iamhankai Forest of Thought Chain of Thought Reasoning
Implementations
- Implementation:OpenRLHF OpenRLHF DPOTrainer
- Implementation:Run llama Llama index BaseVoiceAgentWebsocket
- Implementation:Google deepmind Mujoco USD JointAPI
- Implementation:NVIDIA NeMo Curator TaskPerfUtils
- Implementation:FlagOpen FlagEmbedding LLM Embedder ICL Utils
- Implementation:Openai Openai python Unwrap Webhook Event
- Implementation:Mlflow Mlflow Trace Decorator
- Implementation:Vibrantlabsai Ragas DynamicFewShotPrompt
- Implementation:Datajuicer Data juicer PunctuationNormalizationMapper
- Implementation:Sgl project Sglang Expert Specialization
Heuristics
- Heuristic:Microsoft LoRA Scaling Factor Alpha Over R
- Heuristic:CARLA simulator Carla PID Controller Tuning
- Heuristic:Haifengl Smile BFGS Convergence Tuning
- Heuristic:Huggingface Peft RSLoRA Scaling
- Heuristic:Langchain ai Langgraph Durability Mode Selection
- Heuristic:Astronomer Astronomer cosmos Cache Strategy Optimization
- Heuristic:Huggingface Transformers Label Smoothing Multi Label Warning
- Heuristic:ContextualAI HALOs Batch Size Divisibility
- Heuristic:Haosulab ManiSkill Num Envs Backend Selection
- Heuristic:OWASP Www project top 10 for large language model applications Sandbox Containerization Pattern
Environments
- Environment:Webdriverio Webdriverio Node Runtime Environment
- Environment:Sgl project Sglang GitHub Actions
- Environment:Vllm project Vllm AArch64 CPU
- Environment:FlowiseAI Flowise Queue Mode Environment
- Environment:Microsoft DeepSpeedExamples ZeRO Inference Runtime
- Environment:Predibase Lorax CUDA GPU Runtime
- Environment:Bigscience workshop Petals Python Transformers
- Environment:Dotnet Machinelearning OneDal Acceleration
- Environment:Intel Ipex llm Pipeline Parallel Environment
- Environment:Anthropics Anthropic sdk python Azure Foundry Environment