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:Bitsandbytes foundation Bitsandbytes 4bit QLoRA Inference
- Workflow:Junyanz Pytorch CycleGAN and pix2pix Pix2pix Training
- Workflow:Apache Paimon Blob Storage With Descriptors
- Workflow:Google research Deduplicate text datasets Cross dataset deduplication
- Workflow:Infiniflow Ragflow Chat Application Setup
- Workflow:Spcl Graph of thoughts GoT Keyword Counting Pipeline
- Workflow:Google deepmind Mujoco GPU batched simulation MJX
- Workflow:ARISE Initiative Robosuite Human Demonstration Collection
- Workflow:PacktPublishing LLM Engineers Handbook Digital Data ETL
- Workflow:ARISE Initiative Robosuite Gymnasium RL Integration
Principles
- Principle:Fastai Fastbook Numericalization
- Principle:CarperAI Trlx Offline RL Training
- Principle:Google deepmind Dm control MJCF Model Creation
- Principle:Cleanlab Cleanlab Coteaching Algorithm
- Principle:MaterializeInc Materialize Release Commit and Tagging
- Principle:PacktPublishing LLM Engineers Handbook Content Crawling
- Principle:Microsoft Autogen Team Deployment
- Principle:Microsoft Agent framework Approval Request Presentation
- Principle:Google deepmind Dm control Manipulation Environment Loading
- Principle:TobikoData Sqlmesh Production Deployment With Backfill
Implementations
- Implementation:DistrictDataLabs Yellowbrick ClassPredictionError Visualizer
- Implementation:NVIDIA TransformerEngine Fused Softmax
- Implementation:Guardrails ai Guardrails Configure CLI
- Implementation:Deepseek ai Janus AR Token Generation Loop
- Implementation:Open compass VLMEvalKit Logics Thinking
- Implementation:FlagOpen FlagEmbedding LLM Embedder Eval QA
- Implementation:Infiniflow Ragflow SliderInputFormField Component
- Implementation:Langchain ai Langgraph Pregel Stream With Interrupts
- Implementation:Pyro ppl Pyro UnconditionMessenger
- Implementation:TobikoData Sqlmesh Input Component
Heuristics
- Heuristic:Openai Openai node Stream Usage Interruption
- Heuristic:Openclaw Openclaw Plugin Dependency Gotchas
- Heuristic:Openai Openai python Retry Backoff Strategy
- Heuristic:Nautechsystems Nautilus trader Order Rate Limiting Configuration
- Heuristic:DevExpress Testcafe MacOS Browser Launch Serialization
- Heuristic:DevExpress Testcafe Window Resize Correction
- Heuristic:LLMBook zh LLMBook zh github io IGNORE INDEX Loss Masking
- Heuristic:Junyanz Pytorch CycleGAN and pix2pix Image Size Multiple of Four
- Heuristic:EvolvingLMMs Lab Lmms eval Truncated Image Handling
- Heuristic:FlagOpen FlagEmbedding Gradient Checkpointing Tip
Environments
- Environment:PacktPublishing LLM Engineers Handbook AWS SageMaker GPU Environment
- Environment:Langchain ai Langchain Unit Test Network Isolation
- Environment:Infiniflow Ragflow Python Runtime
- Environment:Truera Trulens OpenAI Provider Environment
- Environment:Kserve Kserve Python Runtime
- Environment:Cypress io Cypress Node Runtime Environment
- Environment:Kubeflow Kubeflow Istio Certmanager Dex Environment
- Environment:Huggingface Transformers PyTorch 24 CUDA
- Environment:Heibaiying BigData Notes Storm 1 2 Environment
- Environment:Deepset ai Haystack HuggingFace Model Environment