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:Openai Evals Implementing a custom completion function
- Workflow:Romsto Speculative Decoding Interactive CLI Comparison
- Workflow:Trailofbits Fickling Pickle Decompilation and Tracing
- Workflow:ARISE Initiative Robomimic Hyperparameter Sweep
- Workflow:SeleniumHQ Selenium Browser Session Setup
- Workflow:Cohere ai Cohere python Tool Use Agentic Chat
- Workflow:Cypress io Cypress E2E Test Execution
- Workflow:Huggingface Trl GRPO Training
- Workflow:Apache Kafka Coordinator Runtime Lifecycle
- Workflow:Openai Openai agents python Guardrails Secured Agent
Principles
- Principle:Datahub project Datahub Metadata Sink Verification
- Principle:Lm sys FastChat Causal LM Loading
- Principle:Triton inference server Server Model Namespacing Testing
- Principle:Mage ai Mage ai Catalog Selection
- Principle:Mlfoundations Open flamingo WebDataset Data Pipeline
- Principle:Kornia Kornia ONNX Model Loading
- Principle:Apache Shardingsphere SPI Refresher Loading
- Principle:LLMBook zh LLMBook zh github io Rotary Position Embedding
- Principle:FMInference FlexLLMGen Decentralized Inference Benchmarking
- Principle:Protectai Llm guard Substring Filtering
Implementations
- Implementation:AUTOMATIC1111 Stable diffusion webui Image Viewer
- Implementation:Anthropics Anthropic sdk python CompletionCreateParams
- Implementation:Open compass VLMEvalKit Cosmos
- Implementation:Langfuse Langfuse Score Application Validation
- Implementation:Cohere ai Cohere python BatchesRawClient
- Implementation:PrefectHQ Prefect Create Markdown Artifact
- Implementation:Ggml org Llama cpp Grammar Header
- Implementation:Avhz RustQuant KNearestNeighbors
- Implementation:Huggingface Datatrove PipelineStats
- Implementation:InternLM Lmdeploy GemmUniversalSm90V2
Heuristics
- Heuristic:Unslothai Unsloth VLLM Memory Utilization
- Heuristic:Wandb Weave Payload Size Limits
- Heuristic:Langgenius Dify API Token Single Flight Caching
- Heuristic:HKUDS AI Trader Sortino Ratio Capping
- Heuristic:Run llama Llama index Finetuning Warmup Steps
- Heuristic:Nautechsystems Nautilus trader Parquet Row Group Tuning
- Heuristic:Marker Inc Korea AutoRAG Module Selection Strategies
- Heuristic:Tensorflow Serving Warning Deprecated CreateTfrtSavedModel Raw
- Heuristic:Apache Beam Thread Pool Parallelism Sizing
- Heuristic:Zai org CogVideo BF16 FP16 Precision Selection
Environments
- Environment:Duckdb Duckdb Extension Distribution Env
- Environment:Huggingface Datasets JAX Integration
- Environment:SqueezeAILab ETS Multi GPU Sglang Runtime
- Environment:Deepset ai Haystack Python Runtime Environment
- Environment:InternLM Lmdeploy Build From Source
- Environment:Apache Spark Kubernetes Runtime
- Environment:Apache Airflow Kubernetes Helm Environment
- Environment:Shiyu coder Kronos HuggingFace Hub Access
- Environment:Risingwavelabs Risingwave Dashboard Node Environment
- Environment:Kserve Kserve Istio Service Mesh