Main Page
27,667
Total Pages
1,118
Workflows
7,697
Principles
16,832
Implementations
1,245
Heuristics
909
Environments
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:Bitsandbytes foundation Bitsandbytes 8bit Optimizer Training
- Workflow:Elevenlabs Elevenlabs python Realtime TTS Streaming
- Workflow:Nightwatchjs Nightwatch Page Object Pattern
- Workflow:Teamcapybara Capybara Custom Selector Definition
- Workflow:Huggingface Datatrove FineWeb Dataset Creation
- Workflow:Microsoft Playwright Network mocking and interception
- Workflow:Princeton nlp Tree of thought llm Baseline comparison
- Workflow:Nautechsystems Nautilus trader Data loading and cataloging
- Workflow:Ggml org Llama cpp Model Perplexity Evaluation
- Workflow:FMInference FlexLLMGen Single GPU Offloaded Inference
Principles
- Principle:Pyro ppl Pyro Amortized Variational Inference
- Principle:Marker Inc Korea AutoRAG Results Dashboard
- Principle:LLMBook zh LLMBook zh github io BPE Tokenization
- Principle:OWASP Www project top 10 for large language model applications Application Architecture Review
- Principle:ARISE Initiative Robosuite Controller Configuration
- Principle:Kubeflow Kubeflow Prerequisites Validation
- Principle:EvolvingLMMs Lab Lmms eval Example Script Creation
- Principle:Haosulab ManiSkill Registration Pattern
- Principle:Langgenius Dify Pipeline Template Selection
- Principle:Pytorch Serve LLM Quick Start
Implementations
- Implementation:Mlc ai Mlc llm Eagle Batch Draft
- Implementation:ArroyoSystems Arroyo Server Common
- Implementation:Astronomer Astronomer cosmos Task Instance Listener
- Implementation:Apache Paimon TorchDataset
- Implementation:Getgauge Taiko Element Base
- Implementation:Speechbrain Speechbrain Prepare Switchboard Transformer
- Implementation:Haotian liu LLaVA ModelWorker Class
- Implementation:BerriAI Litellm Custom Auth Template
- Implementation:Mlc ai Mlc llm Quantization Utils
- Implementation:Sgl project Sglang Export Validation Pattern
Heuristics
- Heuristic:Cypress io Cypress Browser Version Workarounds
- Heuristic:Helicone Helicone Provider URL Regex Priority
- Heuristic:HKUDS AI Trader Market Type Auto Detection
- Heuristic:LaurentMazare Tch rs Safetensors Format Preference
- Heuristic:Dagster io Dagster Record Over Dataclass
- Heuristic:Trailofbits Fickling Force Flag Bypass
- Heuristic:Allenai Open instruct NCCL CUMEM Disable
- Heuristic:Mbzuai oryx Awesome LLM Post training Paper Deduplication Via Dict
- Heuristic:Neuml Txtai Thread Safety Constraints
- Heuristic:CrewAIInc CrewAI LLM Provider Message Workarounds
Environments
- Environment:Kornia Kornia CUDA GPU Environment
- Environment:Huggingface Trl vLLM Generation Environment
- Environment:Ray project Ray Java Build Environment
- Environment:Getgauge Taiko Docker Container
- Environment:PacktPublishing LLM Engineers Handbook VLLM Evaluation Environment
- Environment:Dagster io Dagster PostgreSQL Storage
- Environment:Openai CLIP PyTorch CUDA Runtime
- Environment:Roboflow Rf detr Roboflow Deployment Credentials
- Environment:Onnx Onnx Python Runtime Environment
- Environment:Alibaba ROLL Diffusion Video Environment