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:Vllm project Vllm Vision Language Inference
- Workflow:Liu00222 Open Prompt Injection Prompt Injection Experiment
- Workflow:Tensorflow Tfjs GPT2 Text Generation
- Workflow:Langfuse Langfuse Evaluation pipeline
- Workflow:Mlflow Mlflow LLM Tracing
- Workflow:Truera Trulens RAG With Guardrails
- Workflow:ChenghaoMou Text dedup Benchmark Evaluation
- Workflow:MaterializeInc Materialize Upgrade Testing
- Workflow:Deepspeedai DeepSpeed ZeRO Distributed Training
- Workflow:Ray project Ray Build and Release Pipeline
Principles
- Principle:Speechbrain Speechbrain Whisper Finetuning With LR Scheduling
- Principle:Getgauge Taiko Runtime Configuration
- Principle:Bitsandbytes foundation Bitsandbytes 8bit Quantization Configuration
- Principle:Webdriverio Webdriverio iOS Automation
- Principle:Huggingface Diffusers CI Test Reporting
- Principle:Datahub project Datahub Protobuf Schema Conversion
- Principle:CrewAIInc CrewAI Tool Assignment
- Principle:LaurentMazare Tch rs Custom Dataset Loading
- Principle:Ggml org Llama cpp MemoryAbstraction
- Principle:NVIDIA DALI External Data Source
Implementations
- Implementation:Microsoft Agent framework BaseChatClient As Agent
- Implementation:Onnx Onnx Shape Inference Utils
- Implementation:Online ml River Metrics GeometricMean
- Implementation:Infiniflow Ragflow Docker Prerequisites Check
- Implementation:FMInference FlexLLMGen Prompt Construction Pattern
- Implementation:Bentoml BentoML Deployment Update Get List
- Implementation:Ggml org Ggml Zdnn backend
- Implementation:Alibaba MNN RapidJSON Schema
- Implementation:LaurentMazare Tch rs VarStore Load
- Implementation:LaurentMazare Tch rs Nn Linear
Heuristics
- Heuristic:Alibaba MNN Memory Mode Selection
- Heuristic:DevExpress Testcafe Video Encoding Defaults
- Heuristic:LaurentMazare Tch rs Hidden Dimension Alignment
- Heuristic:Intel Ipex llm NF4 Quantization Best Practice
- Heuristic:Mit han lab Llm awq Kernel Selection Thresholds
- Heuristic:Dagster io Dagster Record Over Dataclass
- Heuristic:Marker Inc Korea AutoRAG Passage Filter Safety Minimum
- Heuristic:Vibrantlabsai Ragas Nest Asyncio Uvloop Compatibility
- Heuristic:Princeton nlp Tree of thought llm Global State Token Counting
- Heuristic:Vespa engine Vespa Maven Parallel Build Optimization
Environments
- Environment:Tensorflow Tfjs Python Converter
- Environment:Intel Ipex llm CPU Finetuning Environment
- Environment:NVIDIA DALI FFmpeg Environment
- Environment:Microsoft Autogen LLM Provider API Keys
- Environment:Pyro ppl Pyro Python PyTorch Core
- Environment:Alibaba ROLL Megatron Training Environment
- Environment:Marker Inc Korea AutoRAG API Keys And Credentials
- Environment:Datahub project Datahub Java Build
- Environment:OpenHands OpenHands SaaS Server Environment
- Environment:Marker Inc Korea AutoRAG GPU PyTorch Environment