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:Pola rs Polars Streaming Large Dataset Processing
- Workflow:Neuml Txtai Agent Orchestration
- Workflow:Guardrails ai Guardrails LLM Output Validation
- Workflow:Duckdb Duckdb Code Generation Pipeline
- Workflow:ThreeSR Awesome Inference Time Scaling Automated Paper Addition
- Workflow:Risingwavelabs Risingwave CDC Data Replication
- Workflow:Microsoft DeepSpeedExamples ZeRO Inference
- Workflow:Mlc ai Web llm Basic Chat Completion
- Workflow:Vllm project Vllm OpenAI Compatible Serving
- Workflow:Google deepmind Mujoco Interactive simulation
Principles
- Principle:Marker Inc Korea AutoRAG Pipeline Query Execution
- Principle:Evidentlyai Evidently Project Configuration
- Principle:Lance format Lance Text Data Preparation
- Principle:Dagster io Dagster Software Defined Assets
- Principle:Ggml org Ggml Backend Interface
- Principle:Princeton nlp Tree of thought llm LLM API Wrapping
- Principle:Webdriverio Webdriverio Command Interception
- Principle:Guardrails ai Guardrails Validator Installation
- Principle:Lm sys FastChat Worker Dispatch Control
- Principle:Togethercomputer Together python Image Generation Request
Implementations
- Implementation:Scikit learn Scikit learn BisectingKMeans
- Implementation:Ray project Ray ParallelActorCallGenerator
- Implementation:Openai Openai python Unwrap Webhook Event
- Implementation:Openai Openai agents python External Model Integration Pattern
- Implementation:Huggingface Transformers Pipeline Forward
- Implementation:Webdriverio Webdriverio SpecReporter Utils
- Implementation:Nightwatchjs Nightwatch Nightwatch CLI Init
- Implementation:Junyanz Pytorch CycleGAN and pix2pix TrainOptions Parse
- Implementation:NVIDIA TransformerEngine Ops L2Normalization
- Implementation:Tensorflow Tfjs Layer Variables
Heuristics
- Heuristic:Treeverse LakeFS Batch Delay Tuning
- Heuristic:Snorkel team Snorkel Binary Only Slicing
- Heuristic:Alibaba ROLL Sequence Packing Alignment
- Heuristic:Apache Druid Explore Compare Query Strategy
- Heuristic:Openclaw Openclaw Retry With Exponential Backoff
- Heuristic:Bigscience workshop Petals Prompt Embeddings Float32 Precision
- Heuristic:Googleapis Python genai API Retry Backoff Strategy
- Heuristic:OpenBMB UltraFeedback Principle Distribution Tuning
- Heuristic:Apache Beam Executor Shutdown Ordering
- Heuristic:Astronomer Astronomer cosmos Static Parser Hang Workaround
Environments
- Environment:Roboflow Rf detr Python GPU Environment
- Environment:DevExpress Testcafe Firefox Marionette
- Environment:Vibrantlabsai Ragas Optional NLP Metrics Environment
- Environment:Neuml Txtai Python Core Environment
- Environment:Openai Openai agents python MCP Dependencies
- Environment:Recommenders team Recommenders Python Core Dependencies
- Environment:Intel Ipex llm XPU Inference Environment
- Environment:Turboderp org Exllamav2 Build Toolchain
- Environment:Sgl project Sglang CPU Runtime
- Environment:Huggingface Open r1 vLLM Server