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:Mit han lab Llm awq AWQ Model Quantization
- Workflow:Huggingface Datatrove Summary Statistics
- Workflow:NVIDIA TransformerEngine Accelerate HF Gemma With TE
- Workflow:Microsoft BIPIA Black Box Defense Evaluation
- Workflow:Nightwatchjs Nightwatch Page Object Pattern
- Workflow:Turboderp org Exllamav2 Interactive Chat
- Workflow:NVIDIA NeMo Aligner RLHF PPO Training
- Workflow:Onnx Onnx Model Validation
- Workflow:Princeton nlp Tree of thought llm ToT BFS experiment
- Workflow:Cypress io Cypress Binary Build and Release
Principles
- Principle:Mit han lab Llm awq W8A8 Vision Encoder Quantization
- Principle:Microsoft DeepSpeedExamples Baseline PyTorch Training
- Principle:MaterializeInc Materialize Container Registry Publishing
- Principle:Huggingface Datasets Pandas Dataset Building
- Principle:Langchain ai Langchain Document Indexing
- Principle:Explodinggradients Ragas Legacy Evaluation Pipeline
- Principle:Eric mitchell Direct preference optimization Evaluation And Sampling
- Principle:Sktime Pytorch forecasting Positional Encoding
- Principle:Huggingface Datatrove Context Window Shuffling
- Principle:LaurentMazare Tch rs Group Normalization
Implementations
- Implementation:Datahub project Datahub DataHubClientException
- Implementation:Scikit learn Scikit learn RANSACRegressor
- Implementation:Ggml org Ggml Ggml opt fit
- Implementation:Langfuse Langfuse API Metrics V2 Schema
- Implementation:Lance format Lance Java JsonFields
- Implementation:LMCache LMCache Redis Adapter
- Implementation:InternLM Lmdeploy Serve Api Server
- Implementation:Google deepmind Dm control Composer Variation
- Implementation:Heibaiying BigData Notes Job SetCombinerClass
- Implementation:Protectai Llm guard Output JSON
Heuristics
- Heuristic:Ollama Ollama Sampling Numerical Stability
- Heuristic:OpenBMB UltraFeedback Score 10 Anomaly Correction
- Heuristic:Langchain ai Langchain Text Splitter Separator Hierarchy
- Heuristic:Openclaw Openclaw Config Cascade Resolution
- Heuristic:Iterative Dvc Run Cache Restoration Strategy
- Heuristic:Intel Ipex llm CCL Distributed Training Tips
- Heuristic:Ucbepic Docetl Optimizer Sample Sizes
- Heuristic:Groq Groq python Streaming Usage Stats
- Heuristic:Princeton nlp SimPO Concatenated Forward Pass
- Heuristic:Ggml org Llama cpp Context Size Alignment
Environments
- Environment:Google deepmind Mujoco C Build Environment
- Environment:VainF Torch Pruning YOLO Pruning Dependencies
- Environment:Triton inference server Server GPU CUDA Runtime
- Environment:Speechbrain Speechbrain HuggingFace Transformers
- Environment:Langfuse Langfuse Redis 7 Queue Cache
- Environment:Marker Inc Korea AutoRAG Korean NLP Dependencies
- Environment:Sail sg LongSpec Inference Environment
- Environment:Sgl project Sglang CPU Runtime
- Environment:Apache Flink Java Build Environment
- Environment:Langgenius Dify Credentials And Env Vars