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:Openclaw Openclaw Agent Message Loop
- Workflow:Elevenlabs Elevenlabs python Text to Speech Generation
- Workflow:Mistralai Client python Chat Completion
- Workflow:Pola rs Polars Streaming Large Dataset Processing
- Workflow:Promptfoo Promptfoo Custom Provider Integration
- Workflow:Groq Groq python Audio Transcription
- Workflow:Predibase Lorax OpenAI Chat Completion
- Workflow:Dotnet Machinelearning ONNX Model Scoring
- Workflow:AUTOMATIC1111 Stable diffusion webui Textual inversion training
- Workflow:Nightwatchjs Nightwatch Component Testing
Principles
- Principle:ARISE Initiative Robosuite Joint Velocity Control
- Principle:Haotian liu LLaVA Batch VQA Inference
- Principle:FMInference FlexLLMGen Optimized Inference Engine
- Principle:Helicone Helicone Verification and Testing
- Principle:Snorkel team Snorkel Labeling Function Analysis
- Principle:Bentoml BentoML Model Versioning
- Principle:Microsoft Agent framework Agent Specialization
- Principle:Heibaiying BigData Notes Flink Streaming Environment
- Principle:Fede1024 Rust rdkafka Custom Async Runtime Integration
- Principle:Ollama Ollama KVCache Encoder Caching
Implementations
- Implementation:Microsoft Onnxruntime Module Optimizer Scheduler Init
- Implementation:Pytorch Serve TransformersSeqClassifierHandler
- Implementation:Ggml org Llama cpp Jinja Utils
- Implementation:Google deepmind Mujoco UI Main
- Implementation:BerriAI Litellm Create File
- Implementation:Microsoft LoRA Run GLUE Training
- Implementation:Allenai Open instruct Submit Eval Jobs
- Implementation:Turboderp org Exllamav2 Build Wheels Release
- Implementation:Elevenlabs Elevenlabs python UnitTestSummaryResponseModel
- Implementation:Neuml Txtai PGText Scoring
Heuristics
- Heuristic:Zai org CogVideo Decord Import Order Bug
- Heuristic:TobikoData Sqlmesh Model Change Categorization
- Heuristic:Langgenius Dify API Token Single Flight Caching
- Heuristic:Datahub project Datahub Spark Databricks Coalescing
- Heuristic:Run llama Llama index Finetuning Warmup Steps
- Heuristic:Openai CLIP L2 Normalization For Cosine Similarity
- Heuristic:Bigscience workshop Petals KV Cache Sizing For Attention Types
- Heuristic:ARISE Initiative Robomimic Data Worker Tuning By Modality
- Heuristic:Snorkel team Snorkel Minimum Three LFs
- Heuristic:Neuml Txtai Batch Size Defaults
Environments
- Environment:OpenRLHF OpenRLHF CUDA GPU Environment
- Environment:Datahub project Datahub Docker Runtime
- Environment:ClickHouse ClickHouse Python3 Test Environment
- Environment:Langgenius Dify Node Frontend Environment
- Environment:OpenRLHF OpenRLHF Flash Attention Environment
- Environment:Tensorflow Tfjs Python Converter
- Environment:Mlfoundations Open flamingo Evaluation Dependencies
- Environment:Mit han lab Llm awq VILA Multimodal Environment
- Environment:Predibase Lorax Docker Container Runtime
- Environment:Getgauge Taiko Node Runtime