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 LLM Int8 Inference
- Workflow:Spcl Graph of thoughts GoT Sorting Pipeline
- Workflow:Pytorch Serve LLM Deployment vLLM
- Workflow:Neuml Txtai Semantic Search
- Workflow:NVIDIA TransformerEngine FSDP Distributed Training
- Workflow:Microsoft Autogen Tool Augmented Agent
- Workflow:ArroyoSystems Arroyo Checkpoint Recovery
- Workflow:CarperAI Trlx RLHF Summarization Pipeline
- Workflow:Microsoft Playwright Codegen test recording
- Workflow:Apache Druid SQL Query Execution
Principles
- Principle:Helicone Helicone Design System
- Principle:Huggingface Datasets Struct Flattening
- Principle:FlowiseAI Flowise Node Parameter Configuration
- Principle:Datajuicer Data juicer LLM Backend Configuration
- Principle:Haosulab ManiSkill Digital Twin Construction
- Principle:Langgenius Dify PluginArchitecture
- Principle:Deepspeedai DeepSpeed Sequence Parallel Attention
- Principle:LLMBook zh LLMBook zh github io Causal LM Loss Computation
- Principle:Arize ai Phoenix Evaluation Result Analysis
- Principle:Eventual Inc Daft Column Input Normalization
Implementations
- Implementation:Huggingface Trl PPO Dataset Tokenization
- Implementation:DevExpress Testcafe Reporter Plugin System
- Implementation:Puppeteer Puppeteer Cdp LifecycleWatcher
- Implementation:Alibaba ROLL VariousDivergence
- Implementation:Scikit learn contrib Imbalanced learn InstanceHardnessThreshold
- Implementation:Scikit learn Scikit learn ClassicalMDS
- Implementation:Nightwatchjs Nightwatch Custom Command Interface
- Implementation:Langchain ai Langchain UV Build
- Implementation:SeleniumHQ Selenium Closure Structs Map
- Implementation:Recommenders team Recommenders NCF Init And Fit
Heuristics
- Heuristic:Run llama Llama index Chunk Size Optimization
- Heuristic:Allenai Open instruct Polyak Reference Update
- Heuristic:Cypress io Cypress V8 Snapshot Memory
- Heuristic:Openai Whisper SDPA Disabling For Attention Extraction
- Heuristic:Mlc ai Mlc llm GPU Memory Budget Tuning
- Heuristic:Microsoft Agent framework Declaration Only Tools Pattern
- Heuristic:Ggml org Llama cpp GPU Layer Offloading Verification
- Heuristic:Huggingface Peft RSLoRA Scaling
- Heuristic:Apache Druid Capability Detection Strategy
- Heuristic:Unstructured IO Unstructured Golden File Diff
Environments
- Environment:VainF Torch Pruning PyTorch Python Core
- Environment:Openclaw Openclaw Node 22 Runtime
- Environment:Spotify Luigi Tornado Web Server
- Environment:ChenghaoMou Text dedup Python 3 12 Environment
- Environment:Sgl project Sglang Grafana
- Environment:LMCache LMCache NIXL Transfer Library
- Environment:Apache Spark Kubernetes Runtime
- Environment:DevExpress Testcafe Chrome Browser
- Environment:LLMBook zh LLMBook zh github io Data Processing Environment
- Environment:Gretelai Gretel synthetics Python Base Environment