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:Trailofbits Fickling Pickle Safety Analysis
- Workflow:Mlflow Mlflow GenAI Evaluation
- Workflow:Apache Flink File Sink Pipeline
- Workflow:Online ml River Drift Adaptive Classification
- Workflow:Cohere ai Cohere python AWS Bedrock Deployment
- Workflow:Cleanlab Cleanlab Multiannotator Consensus
- Workflow:Huggingface Datasets Format Conversion
- Workflow:Ollama Ollama Model Registry Operations
- Workflow:Iamhankai Forest of Thought CGDM Post Processing
- Workflow:Sail sg LongSpec Speculative Decoding Inference
Principles
- Principle:Deepset ai Haystack Optional Dependency Handling
- Principle:Pytorch Serve Semantic Segmentation
- Principle:Vllm project Vllm Speculation Metrics Evaluation
- Principle:Apache Flink File Compaction Strategy
- Principle:LaurentMazare Tch rs Recurrent Neural Network
- Principle:Ollama Ollama KVCache Causal Attention
- Principle:Openai Openai node Tool Execution Loop
- Principle:Ollama Ollama Anthropic Trace Logging
- Principle:Bigscience workshop Petals Optimizer Setup
- Principle:Iterative Dvc Cache Transfer
Implementations
- Implementation:Lance format Lance EncodingsIo
- Implementation:MarketSquare Robotframework browser Network Idle Transformer
- Implementation:Haosulab ManiSkill Fetch
- Implementation:Google deepmind Dm control Suite Quadruped
- Implementation:Interpretml Interpret Group Importance
- Implementation:Ggml org Llama cpp Jinja Parser
- Implementation:Arize ai Phoenix Legacy Templates
- Implementation:TobikoData Sqlmesh Generate Test
- Implementation:Guardrails ai Guardrails Telemetry Common
- Implementation:Openai Openai python Response Reasoning Summary Part Done
Heuristics
- Heuristic:Openai Openai python Streaming Resource Management
- Heuristic:Liu00222 Open Prompt Injection Defense Strategy Selection
- Heuristic:Cypress io Cypress Browser Version Workarounds
- Heuristic:Ggml org Ggml Memory Allocation Strategy
- Heuristic:LLMBook zh LLMBook zh github io DPO Beta Hyperparameter
- Heuristic:Apache Hudi Record Level Index Optimization
- Heuristic:Marker Inc Korea AutoRAG Empty Result Fallback
- Heuristic:Lm sys FastChat Greedy Decoding Temperature Threshold
- Heuristic:Risingwavelabs Risingwave Memory Cache Eviction Policy
- Heuristic:ArroyoSystems Arroyo Async UDF Concurrency
Environments
- Environment:Ray project Ray Java Build Environment
- Environment:Langgenius Dify Docker Compose Environment
- Environment:Cleanlab Cleanlab Datalab Dependencies
- Environment:BerriAI Litellm Docker Deployment
- Environment:VainF Torch Pruning LLM Pruning Dependencies
- Environment:Onnx Onnx Python Runtime Environment
- Environment:Huggingface Datatrove IO Dependencies
- Environment:Onnx Onnx Cpp Build Environment
- Environment:PacktPublishing LLM Engineers Handbook Docker MongoDB Qdrant Infrastructure
- Environment:NVIDIA TransformerEngine CUDA Toolkit Requirements