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:Duckdb Duckdb Code Generation Pipeline
- Workflow:Haotian liu LLaVA LoRA Finetuning
- Workflow:Evidentlyai Evidently Monitoring Dashboard Setup
- Workflow:Apache Beam Twister2 Batch Execution
- Workflow:Huggingface Peft LoRA Embedding Semantic Search
- Workflow:Danijar Dreamerv3 Distributed Parallel Training
- Workflow:Puppeteer Puppeteer Browser Installation And Management
- Workflow:Anthropics Anthropic sdk python Basic Message Conversation
- Workflow:Turboderp org Exllamav2 Multimodal Vision Inference
- Workflow:Gretelai Gretel synthetics ACTGAN Tabular Synthesis
Principles
- Principle:Unstructured IO Unstructured Pipeline Output Validation
- Principle:Triton inference server Server Multi Server Deployment
- Principle:Puppeteer Puppeteer Code Coverage Collection
- Principle:Mlc ai Web llm Dependency Version Pinning
- Principle:DataExpert io Data engineer handbook DataFrame Write To Table
- Principle:Evidentlyai Evidently Report Execution
- Principle:ClickHouse ClickHouse Type Safe Wrappers
- Principle:Tensorflow Tfjs Model Evaluation And Deployment
- Principle:Ggml org Ggml Autoregressive Generation
- Principle:Huggingface Diffusers DreamBooth Export
Implementations
- Implementation:Elevenlabs Elevenlabs python VoiceSamplePreviewResponseModel
- Implementation:Heibaiying BigData Notes HBaseUtils PutRow
- Implementation:Explodinggradients Ragas InMemoryBackend Class
- Implementation:Princeton nlp SimPO Decontaminate Humaneval
- Implementation:HKUDS AI Trader MCPServiceManager Start All Services
- Implementation:Ucbepic Docetl FrontendTypes
- Implementation:Scikit learn Scikit learn SphinxConf
- Implementation:Haosulab ManiSkill QuadrupedReach
- Implementation:Apache Beam Twister2Runner ZipDependencies
- Implementation:Google deepmind Mujoco Engine Plugin
Heuristics
- Heuristic:ChenghaoMou Text dedup Mersenne Prime Backward Compatibility
- Heuristic:Openai CLIP CLIP Normalization Constants
- Heuristic:Guardrails ai Guardrails Guard History Memory Management
- Heuristic:Teamcapybara Capybara Frozen Time Detection
- Heuristic:Triton inference server Server Concurrency Throughput Rule
- Heuristic:Huggingface Transformers Gradient Checkpointing Memory Tradeoff
- Heuristic:Interpretml Interpret Memory Budget Heuristic
- Heuristic:Ggml org Ggml Gradient Accumulation Batch Sizing
- Heuristic:Deepset ai Haystack Pipeline Max Runs Safety Limit
- Heuristic:Mbzuai oryx Awesome LLM Post training Paper Deduplication Via Dict
Environments
- Environment:Openai Evals OpenAI API Configuration
- Environment:Alibaba MNN GPU OpenCL Environment
- Environment:FlagOpen FlagEmbedding GPU Accelerator Environment
- Environment:ArroyoSystems Arroyo PostgreSQL Database
- Environment:Langgenius Dify Redis And Celery Environment
- Environment:OpenBMB UltraFeedback Python GPU Environment
- Environment:Kserve Kserve VLLM Runtime
- Environment:Mbzuai oryx Awesome LLM Post training Git CLI
- Environment:Mlc ai Mlc llm CUDA GPU Environment
- Environment:Tencent Ncnn Vulkan Environment