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:Princeton nlp Tree of thought llm Adding new task
- Workflow:Openai Openai python Audio Processing
- Workflow:Mlflow Mlflow Prompt Management
- Workflow:Nightwatchjs Nightwatch Component Testing
- Workflow:Huggingface Datasets Dataset Preprocessing
- Workflow:Cohere ai Cohere python Model Finetuning
- Workflow:Mlfoundations Open flamingo Few Shot Evaluation
- Workflow:Datajuicer Data juicer LLM Powered Data Generation
- Workflow:Groq Groq python Chat Completion
- Workflow:Deepset ai Haystack RAG Evaluation Pipeline
Principles
- Principle:Dotnet Machinelearning Hardware Accelerated Training
- Principle:Unslothai Unsloth Synthetic Data Generation
- Principle:Junyanz Pytorch CycleGAN and pix2pix Dataset Pair Alignment
- Principle:Unslothai Unsloth LoRA Adapter Injection
- Principle:Ggml org Llama cpp Sampling
- Principle:Puppeteer Puppeteer Device Emulation
- Principle:Fastai Fastbook Text Data Preparation
- Principle:Mlc ai Web llm Chrome Extension Manifest
- Principle:Protectai Llm guard Output Scanning
- Principle:Openai Openai python Fine Tuning Job Monitoring
Implementations
- Implementation:Apache Paimon CatalogEnvironment
- Implementation:Cleanlab Cleanlab Compute Confident Joint
- Implementation:Bitsandbytes foundation Bitsandbytes GlobalOptimManager
- Implementation:Haosulab ManiSkill AllegroHand
- Implementation:Google deepmind Mujoco MJWarp Collision Convex
- Implementation:Teamcapybara Capybara Spec Rack Test
- Implementation:Mlflow Mlflow Prompt Version Entity
- Implementation:CrewAIInc CrewAI Code Docs Search Tool
- Implementation:Isaac sim IsaacGymEnvs Load Asset Meshes In Warp
- Implementation:Zai org CogVideo IFNet HDv3
Heuristics
- Heuristic:Mlc ai Mlc llm Metal KV Cache Capacity Limit
- Heuristic:Deepset ai Haystack BM25 Score Scaling
- Heuristic:LLMBook zh LLMBook zh github io Deduplication Ngram Threshold
- Heuristic:Langfuse Langfuse Eval Loop Prevention
- Heuristic:Ucbepic Docetl Optimizer Sample Sizes
- Heuristic:Microsoft Semantic kernel Function Choice Behavior Selection
- Heuristic:Romsto Speculative Decoding Ngram Order Selection
- Heuristic:Vibrantlabsai Ragas Warning Deprecated Legacy LLM Wrappers
- Heuristic:Shiyu coder Kronos Sampling Temperature Tuning
- Heuristic:Langfuse Langfuse Fail Open Resilience Pattern
Environments
- Environment:Datahub project Datahub Spark Lineage Environment
- Environment:Kubeflow Pipelines Kubernetes Cluster
- Environment:Intel Ipex llm Build Environment
- Environment:Pytorch Serve DeepSpeed Environment
- Environment:Unslothai Unsloth CUDA VLLM
- Environment:ARISE Initiative Robomimic Robosuite Simulation Backend
- Environment:Kserve Kserve Leader Worker Set
- Environment:Microsoft Onnxruntime CUDA GPU Environment
- Environment:Google research Deduplicate text datasets Rust Cargo Build Environment
- Environment:Triton inference server Server TRT LLM Deployment