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:PacktPublishing LLM Engineers Handbook Feature Engineering
- Workflow:Eric mitchell Direct preference optimization Custom Dataset Integration
- Workflow:Langgenius Dify Application Creation
- Workflow:Shiyu coder Kronos CSV Finetuning
- Workflow:ChenghaoMou Text dedup Benchmark Evaluation
- Workflow:Mlflow Mlflow Model Logging and Registry
- Workflow:Deepspeedai DeepSpeed Hybrid Engine RLHF Training
- Workflow:Haosulab ManiSkill RL Training with PPO
- Workflow:Norrrrrrr lyn WAInjectBench Embedding Classifier Training
- Workflow:SeldonIO Seldon core Model Explainability
Principles
- Principle:Mit han lab Llm awq Checkpoint Preparation
- Principle:Onnx Onnx Numpy Tensor Conversion
- Principle:Sktime Pytorch forecasting NHiTS Architecture
- Principle:Interpretml Interpret Decision Tree Classification
- Principle:Farama Foundation Gymnasium Batched Environment Interaction
- Principle:FlagOpen FlagEmbedding Multi Task Retrieval Embedder
- Principle:Kserve Kserve Pipeline Validation
- Principle:Openai Openai node Tool Loop Resolution
- Principle:FMInference FlexLLMGen Model Replacement Policy
- Principle:Unslothai Unsloth Synthetic Data Generation
Implementations
- Implementation:Mlc ai Mlc llm Model Metadata Impl
- Implementation:Hpcaitech ColossalAI Load QA Chain
- Implementation:Openai Openai python Response Reasoning Summary Text Done
- Implementation:Risingwavelabs Risingwave StreamChunkIterator
- Implementation:Alibaba MNN Protobuf Extension Set H
- Implementation:Infiniflow Ragflow ChunkCreatingModal Component
- Implementation:Lance format Lance FixedSizeListEncoding
- Implementation:Predibase Lorax Router Client Lib
- Implementation:Cohere ai Cohere python EmbedJobsClient Create
- Implementation:Tencent Ncnn SimpleOCV
Heuristics
- Heuristic:Cohere ai Cohere python Tokenizer Cache With TTL
- Heuristic:Run llama Llama index Chunk Size Optimization
- Heuristic:Vespa engine Vespa Maven Parallel Build Optimization
- Heuristic:Fede1024 Rust rdkafka Multi Version Dependency Hazard
- Heuristic:Togethercomputer Together python Multipart Upload Strategy
- Heuristic:Avhz RustQuant Finite Difference Grid Sizing
- Heuristic:TobikoData Sqlmesh Snapshot TTL Defaults
- Heuristic:Teamcapybara Capybara Async Waiting And Retry
- Heuristic:Mlfoundations Open flamingo Gradient Clipping Max Norm
- Heuristic:Hpcaitech ColossalAI CUDA Device Max Connections Tip
Environments
- Environment:Vespa engine Vespa Java 17 Build Runtime
- Environment:Facebookresearch Habitat lab HITL Runtime Environment
- Environment:Turboderp org Exllamav2 Build Toolchain
- Environment:Huggingface Datatrove Processing Dependencies
- Environment:Tencent Ncnn Vulkan Environment
- Environment:Mage ai Mage ai Singer SDK And Joblib Runtime
- Environment:Langchain ai Langchain OpenAI API Credentials
- Environment:Nightwatchjs Nightwatch BrowserStack Cloud
- Environment:Vllm project Vllm CUDA GPU Runtime
- Environment:Microsoft Onnxruntime Windows Build Environment