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:Huggingface Transformers Model Quantization
- Workflow:Mistralai Client python Azure Chat Completion
- Workflow:Puppeteer Puppeteer Page Screenshot Capture
- Workflow:PeterL1n BackgroundMattingV2 Training pipeline
- Workflow:Alibaba ROLL Agentic RL Training Pipeline
- Workflow:Microsoft Autogen Swarm Agent Handoff
- Workflow:TobikoData Sqlmesh Plan and apply deployment
- Workflow:Cohere ai Cohere python Streaming Chat
- Workflow:Turboderp org Exllamav2 EXL2 Model Conversion
- Workflow:Nightwatchjs Nightwatch Page Object Pattern
Principles
- Principle:Huggingface Diffusers LoRA Adapter Injection
- Principle:Liu00222 Open Prompt Injection Conditional Probability Computation
- Principle:Mlflow Mlflow API Compatibility Checking
- Principle:FMInference FlexLLMGen Inference Module Replacement
- Principle:Helicone Helicone Schema Mapping
- Principle:Microsoft Semantic kernel Python SDK Package Configuration
- Principle:Webdriverio Webdriverio ServiceArchitecture
- Principle:Kubeflow Kubeflow Multi User Configuration
- Principle:Facebookresearch Audiocraft Pretrained Model Loading
- Principle:Langchain ai Langchain Vector Store Initialization
Implementations
- Implementation:Online ml River Compose Renamer
- Implementation:Togethercomputer Together python Evaluation Types
- Implementation:Open compass VLMEvalKit BMMR Utils
- Implementation:Mlflow Mlflow Exceptions
- Implementation:Ggml org Llama cpp Compare Logits
- Implementation:Speechbrain Speechbrain Interpret AMT
- Implementation:ArroyoSystems Arroyo Rpc Core
- Implementation:Teamcapybara Capybara Edge Driver Specialization
- Implementation:Mit han lab Llm awq Split and repack
- Implementation:Microsoft DeepSpeedExamples Stable Diffusion LoRA Distillation
Heuristics
- Heuristic:CARLA simulator Carla Walker Spawn Vertical Offset
- Heuristic:OpenBMB UltraFeedback API Retry Strategy
- Heuristic:Mlflow Mlflow Prompt Cache Tuning
- Heuristic:Langchain ai Langgraph Stream Mode Selection
- Heuristic:Dagster io Dagster Retry Strategy Configuration
- Heuristic:Marker Inc Korea AutoRAG Module Selection Strategies
- Heuristic:Princeton nlp Tree of thought llm Duplicate Candidate Zeroing
- Heuristic:Norrrrrrr lyn WAInjectBench Zero Vector Fallback Failed Embeddings
- Heuristic:DevExpress Testcafe Assertion Retry Timing
- Heuristic:Open compass VLMEvalKit Judge Model Selection By Dataset
Environments
- Environment:Intel Ipex llm vLLM XPU Serving Environment
- Environment:Apache Kafka Docker Build Environment
- Environment:Neuml Txtai Docker Deployment Environment
- Environment:Togethercomputer Together python Python SDK Runtime
- Environment:Promptfoo Promptfoo Python Runtime
- Environment:LLMBook zh LLMBook zh github io HuggingFace Transformers Stack
- Environment:Ggml org Ggml CUDA GPU Environment
- Environment:Risingwavelabs Risingwave Python Tooling Environment
- Environment:Apache Shardingsphere Calcite Federation Engine
- Environment:Volcengine Verl Megatron Core Environment