Main Page
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:LMCache LMCache P2P KV Cache Sharing
- Workflow:Ollama Ollama OpenAI API Compatibility
- Workflow:TobikoData Sqlmesh Environment management
- Workflow:Evidentlyai Evidently Data Drift Monitoring
- Workflow:LaurentMazare Tch rs Pretrained Image Classification
- Workflow:Teamcapybara Capybara RSpec Integration Setup
- Workflow:Apache Spark Release Process
- Workflow:Shiyu coder Kronos Batch Prediction
- Workflow:TobikoData Sqlmesh Incremental model development
- Workflow:Ray project Ray Serve Deployment
Principles
- Principle:Explodinggradients Ragas LLM Provider Abstraction
- Principle:Cypress io Cypress Testing Type Selection
- Principle:Triton inference server Server Memory Allocation Testing
- Principle:Alibaba ROLL Video Generation and Reward
- Principle:Microsoft Semantic kernel Vector Similarity Search
- Principle:Treeverse LakeFS API Authorization Specification
- Principle:Langgenius Dify ContentModeration
- Principle:Bitsandbytes foundation Bitsandbytes Int8 Vectorwise Quantization
- Principle:Mit han lab Llm awq Fused Attention Optimization
- Principle:Danijar Dreamerv3 Random Baseline Agent
Implementations
- Implementation:ClickHouse ClickHouse Phdr Cache
- Implementation:Apache Paimon Preconditions
- Implementation:Huggingface Diffusers DreamBooth Args
- Implementation:Risingwavelabs Risingwave DbzCdcEngineRunner Start
- Implementation:Openai Openai python Web Search Tool Param
- Implementation:Lm sys FastChat Get Peft State Maybe Zero 3
- Implementation:FlagOpen FlagEmbedding LLM Embedder Retrieval Trainer
- Implementation:Langfuse Langfuse BullMQ Queue Factory
- Implementation:NVIDIA DALI HW Decoder Benchmark
- Implementation:Langchain ai Langchain Perplexity Output Parsers
Heuristics
- Heuristic:PacktPublishing LLM Engineers Handbook RAG Retrieval Parameters
- Heuristic:Cohere ai Cohere python HTTP Retry Backoff Strategy
- Heuristic:Microsoft Playwright Browser Specific Workarounds
- Heuristic:Snorkel team Snorkel NLP Preprocessor Memoization
- Heuristic:DataTalksClub Data engineering zoomcamp CSV Chunk Size Optimization
- Heuristic:Datahub project Datahub Git Worktree Gradle Fix
- Heuristic:Apache Druid Cluster Health Diagnostic Thresholds
- Heuristic:Run llama Llama index Finetuning Warmup Steps
- Heuristic:Microsoft Autogen Model Context Limiting
- Heuristic:Elevenlabs Elevenlabs python Client Timeout Configuration
Environments
- Environment:Ggml org Llama cpp Vulkan GPU Environment
- Environment:Mage ai Mage ai Singer SDK And Joblib Runtime
- Environment:Speechbrain Speechbrain Speech Enhancement Dependencies
- Environment:Roboflow Rf detr Python GPU Environment
- Environment:DistrictDataLabs Yellowbrick Optional NLP Dependencies
- Environment:Microsoft Onnxruntime Sklearn Conversion Environment
- Environment:AUTOMATIC1111 Stable diffusion webui Python And PyTorch Runtime
- Environment:Scikit learn contrib Imbalanced learn Python Scikit learn
- Environment:Dotnet Machinelearning Native Build Toolchain
- Environment:TobikoData Sqlmesh Dbt Compatibility