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:Iterative Dvc Remote Data Sync
- Workflow:Intel Ipex llm QLoRA Finetuning
- Workflow:MaterializeInc Materialize dbt Integration
- Workflow:Elevenlabs Elevenlabs python Realtime TTS Streaming
- Workflow:Vllm project Vllm Speculative Decoding
- Workflow:Turboderp org Exllamav2 Interactive Chat
- Workflow:Google research Deduplicate text datasets Wiki40B TFDS deduplication
- Workflow:Vllm project Vllm Structured Output Generation
- Workflow:PrefectHQ Prefect AI Data Analyst Agent
- Workflow:Liu00222 Open Prompt Injection DataSentinel Detection
Principles
- Principle:Mit han lab Llm awq Distributed Model Serving
- Principle:Google deepmind Dm control Environment Wrapping
- Principle:NVIDIA NeMo Curator Video Frame Extraction
- Principle:Openai Evals Language Modeling Evaluation
- Principle:Microsoft Autogen Graph Topology Design
- Principle:Getgauge Taiko Text Field Selection
- Principle:Microsoft Onnxruntime Inference Session Creation
- Principle:Haosulab ManiSkill Scene Construction
- Principle:Microsoft Playwright Test Configuration
- Principle:Truera Trulens Custom App Wrapping
Implementations
- Implementation:Kubeflow Pipelines Convert CSV To Parquet Op
- Implementation:Promptfoo Promptfoo Table Renderer
- Implementation:FlagOpen FlagEmbedding AbsReranker Compute Score
- Implementation:Tensorflow Tfjs Rescaling Layer
- Implementation:Langfuse Langfuse ExtractVariablesFromTracingData
- Implementation:Groq Groq python Translations Create
- Implementation:Kornia Kornia Hyperplane
- Implementation:Onnx Onnx Version Converter Convert Version
- Implementation:Pytorch Serve Custom Metrics Handler
- Implementation:Iterative Dvc Build Graph
Heuristics
- Heuristic:Openai Openai python Timeout Connection Defaults
- Heuristic:NVIDIA NeMo Aligner Adam State Offloading Tip
- Heuristic:InternLM Lmdeploy Backend Selection Strategy
- Heuristic:Ucbepic Docetl Reduce Parallel Fold Tuning
- Heuristic:Huggingface Alignment handbook Gradient Checkpointing Use Cache
- Heuristic:Turboderp org Exllamav2 Attention Backend Selection
- Heuristic:Apache Druid Explore Compare Query Strategy
- Heuristic:Marker Inc Korea AutoRAG Hybrid Retrieval Score Normalization
- Heuristic:Mlc ai Mlc llm FlashInfer KV Cache Fallback
- Heuristic:Deepseek ai Janus Image Generation Prompt Tips
Environments
- Environment:Openai Openai python Azure OpenAI
- Environment:Haosulab ManiSkill Real Robot LeRobot Deps
- Environment:Ray project Ray Docker GPU Environment
- Environment:AnswerDotAI RAGatouille GPU CUDA Runtime
- Environment:Protectai Llm guard ONNX Runtime Acceleration
- Environment:Apache Hudi Flink Runtime Environment
- Environment:ThreeSR Awesome Inference Time Scaling Python Runtime Environment
- Environment:Huggingface Datatrove IO Dependencies
- Environment:HKUDS AI Trader API Credentials
- Environment:Volcengine Verl SGLang Rollout Environment