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:Anthropics Anthropic sdk python Tool Use Integration
- Workflow:Cohere ai Cohere python AWS Bedrock Deployment
- Workflow:Puppeteer Puppeteer PDF Generation
- Workflow:Heibaiying BigData Notes Spark SQL Data Analysis
- Workflow:Apache Flink Async Sink Lifecycle
- Workflow:Lm sys FastChat ShareGPT Data Pipeline
- Workflow:NVIDIA NeMo Curator Fuzzy Deduplication
- Workflow:Kserve Kserve LLM Disaggregated Serving
- Workflow:Trailofbits Fickling PyTorch Payload Injection
- Workflow:Alibaba MNN Python Model Inference
Principles
- Principle:Lance format Lance Data Ingestion
- Principle:Sktime Pytorch forecasting TFT V2 Architecture
- Principle:Pytorch Serve Instance Segmentation
- Principle:Microsoft Agent framework Tool Approval Configuration
- Principle:Deepset ai Haystack Pipeline Orchestration
- Principle:ARISE Initiative Robosuite Gripper Model Design
- Principle:Huggingface Datasets Dataset Split Inspection
- Principle:BerriAI Litellm Training Data Preparation
- Principle:OpenGVLab InternVL Distributed Worker Management
- Principle:Bitsandbytes foundation Bitsandbytes Matmul Performance Estimation
Implementations
- Implementation:Cohere ai Cohere python AwsCohereError
- Implementation:SeleniumHQ Selenium PortProber
- Implementation:Promptfoo Promptfoo Feedback
- Implementation:Microsoft Onnxruntime CPU MpiRecv
- Implementation:DistrictDataLabs Yellowbrick InterclusterDistance Visualizer
- Implementation:Webdriverio Webdriverio TestFnWrapper
- Implementation:Spotify Luigi FTPTarget
- Implementation:ArroyoSystems Arroyo Validate UDF
- Implementation:Interpretml Interpret StitchWidget TS
- Implementation:Huggingface Transformers LoraConfig
Heuristics
- Heuristic:OpenGVLab InternVL Packed Training Buffer Management
- Heuristic:Junyanz Pytorch CycleGAN and pix2pix Test Train Option Consistency
- Heuristic:Openai Openai agents python Tool Choice Reset Prevents Loops
- Heuristic:Apache Beam Warning Deprecated Twister2 Runner
- Heuristic:LLMBook zh LLMBook zh github io LoRA Initialization Strategy
- Heuristic:Obss Sahi Overlap Ratio Selection
- Heuristic:Openai Openai python Streaming Resource Management
- Heuristic:TobikoData Sqlmesh Model Change Categorization
- Heuristic:Cypress io Cypress V8 Snapshot Memory
- Heuristic:Princeton nlp SimPO Hyperparameter Tuning
Environments
- Environment:Interpretml Interpret Blackbox Explainer Dependencies
- Environment:Ray project Ray Docker GPU Environment
- Environment:Apache Flink Python PyFlink Environment
- Environment:Huggingface Diffusers Quantization Environment
- Environment:Volcengine Verl Ray Distributed Environment
- Environment:Tencent Ncnn PyTorch Environment
- Environment:Langfuse Langfuse S3 Compatible Storage
- Environment:LMCache LMCache CUDA GPU Runtime
- Environment:Apache Paimon Cloud Storage Credentials
- Environment:Openai CLIP PyTorch CUDA Runtime