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:Gretelai Gretel synthetics DataFrame Batch Synthesis
- Workflow:OpenGVLab InternVL LoRA Finetuning
- Workflow:Scikit learn contrib Imbalanced learn Imbalanced Model Evaluation
- Workflow:Mlfoundations Open flamingo Data Preparation
- Workflow:Facebookresearch Audiocraft MusicGen Training Pipeline
- Workflow:Apache Kafka PR Merge And Backport
- Workflow:Google deepmind Dm control Control Suite RL Training
- Workflow:Online ml River Drift Adaptive Classification
- Workflow:Iterative Dvc Plot Visualization
- Workflow:Microsoft Semantic kernel Plugin Integration And Function Calling
Principles
- Principle:HKUDS AI Trader Trading Outcome Recording
- Principle:LaurentMazare Tch rs FFI Collection Traits
- Principle:Ucbepic Docetl Hierarchical Document Clustering
- Principle:Haotian liu LLaVA Custom Dataset Formatting
- Principle:FMInference FlexLLMGen Model Weight Downloading
- Principle:NVIDIA NeMo Aligner Reward Model Architecture Selection
- Principle:Heibaiying BigData Notes Kafka Message Sending
- Principle:Langgenius Dify ReactLifecycleManagement
- Principle:CrewAIInc CrewAI Manager Agent Configuration
- Principle:NVIDIA DALI PyTorch Iterator
Implementations
- Implementation:Fede1024 Rust rdkafka Producer Transaction Methods
- Implementation:Iterative Dvc DataCloud Get Remote
- Implementation:Webdriverio Webdriverio BStackCleanup Class
- Implementation:Facebookresearch Habitat lab ArticulatedAgentInterface
- Implementation:Mlc ai Mlc llm Bundle weight
- Implementation:Pyro ppl Pyro Autoname Mixture
- Implementation:Avhz RustQuant Exotic Option Constructors
- Implementation:Bentoml BentoML Framework PyTorch Lightning
- Implementation:Bentoml BentoML Public API Module
- Implementation:Kornia Kornia ImageStitcher
Heuristics
- Heuristic:Vibrantlabsai Ragas Reasoning Model Parameter Constraints
- Heuristic:Teamcapybara Capybara Frozen Time Detection
- Heuristic:Liu00222 Open Prompt Injection Attack Effectiveness Hierarchy
- Heuristic:Bentoml BentoML Platform Serving Caveats
- Heuristic:Pola rs Polars Lazy Over Eager Preference
- Heuristic:OpenRLHF OpenRLHF Packing Samples Efficiency Tip
- Heuristic:LLMBook zh LLMBook zh github io Deduplication Ngram Threshold
- Heuristic:Marker Inc Korea AutoRAG Data Format Requirements
- Heuristic:Fastai Fastbook Mixup Data Augmentation
- Heuristic:Mbzuai oryx Awesome LLM Post training Excel Sheet Name Truncation
Environments
- Environment:Unstructured IO Unstructured Libmagic
- Environment:Vibrantlabsai Ragas LLM Provider Credentials
- Environment:Mlc ai Web llm Node Build Toolchain
- Environment:AnswerDotAI RAGatouille GPU CUDA Runtime
- Environment:Getgauge Taiko Docker Container
- Environment:Webdriverio Webdriverio Node Runtime Environment
- Environment:TobikoData Sqlmesh Snowflake Connection
- Environment:Guardrails ai Guardrails OpenTelemetry Tracing
- Environment:Predibase Lorax Python Server Dependencies
- Environment:BerriAI Litellm Observability Stack