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:Cohere ai Cohere python Chat Completion
- Workflow:Dotnet Machinelearning Binary Classification Pipeline
- Workflow:MaterializeInc Materialize CI Pipeline Generation
- Workflow:Kornia Kornia Image Feature Matching
- Workflow:Microsoft Playwright AI agent driven testing
- Workflow:AUTOMATIC1111 Stable diffusion webui Hypernetwork training
- Workflow:Cleanlab Cleanlab Datalab Dataset Audit
- Workflow:Run llama Llama index Evaluation Pipeline
- Workflow:Datahub project Datahub Java SDK Metadata Emission
- Workflow:Openai Openai agents python Basic Agent Execution
Principles
- Principle:FMInference FlexLLMGen Distributed Job Runner
- Principle:Romsto Speculative Decoding Ngram Storage
- Principle:Heibaiying BigData Notes MapReduce Map Phase
- Principle:Microsoft Semantic kernel Vector Similarity Search
- Principle:Ggml org Llama cpp Model Loading
- Principle:Duckdb Duckdb Extension Loading Verification
- Principle:Alibaba ROLL DPO Validation
- Principle:Shiyu coder Kronos Qlib Training Dataset
- Principle:Spcl Graph of thoughts Thought Aggregation
- Principle:Speechbrain Speechbrain Transformer ASR Training
Implementations
- Implementation:Risingwavelabs Risingwave GlueCredentialProvider
- Implementation:Huggingface Diffusers PeftAdapterMixin Add Adapter
- Implementation:Microsoft LoRA Utils Multiple Choice
- Implementation:Langgenius Dify Component Analyzer
- Implementation:Apache Shardingsphere ShadowRuleBuilder Build
- Implementation:Sgl project Sglang Speculative Decoding Ops
- Implementation:TA Lib Ta lib python Stream Buffer Pattern
- Implementation:Treeverse LakeFS Java SDK JSON
- Implementation:Cohere ai Cohere python FinetuneDatasetMetrics Model
- Implementation:InternLM Lmdeploy Interval
Heuristics
- Heuristic:Facebookresearch Habitat lab DDPPO Straggler Preemption
- Heuristic:Sgl project Sglang Attention Backend Selection
- Heuristic:NVIDIA DALI Last Batch Policy Selection
- Heuristic:ChenghaoMou Text dedup Fingerprint Batch Size One
- Heuristic:Hiyouga LLaMA Factory Gradient Checkpointing Memory Optimization
- Heuristic:Norrrrrrr lyn WAInjectBench L2 Normalize CLIP Embeddings
- Heuristic:Spotify Luigi Batch Parameter Aggregation
- Heuristic:Huggingface Datasets Cache Fingerprinting Tips
- Heuristic:ARISE Initiative Robomimic BatchNorm To GroupNorm For EMA
- Heuristic:Sktime Pytorch forecasting Early Stopping Patience
Environments
- Environment:OpenHands OpenHands Third Party Runtime Credentials
- Environment:Vespa engine Vespa CMake Cpp23 Build Environment
- Environment:CarperAI Trlx NeMo Megatron
- Environment:LLMBook zh LLMBook zh github io Bitsandbytes Quantization Environment
- Environment:Microsoft DeepSpeedExamples RLHF Training Environment
- Environment:Unstructured IO Unstructured All Docs
- Environment:Duckdb Duckdb CMake Build Toolchain
- Environment:ContextualAI HALOs CUDA 12 1 Training Environment
- Environment:Ucbepic Docetl Docker Deployment
- Environment:Openai Openai agents python MCP Dependencies