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:Teamcapybara Capybara RSpec Integration Setup
- Workflow:Recommenders team Recommenders Algorithm Benchmarking
- Workflow:Openai Whisper Word Level Timestamps
- Workflow:Huggingface Trl PPO RLHF Training
- Workflow:Google deepmind Mujoco GPU batched simulation MJX
- Workflow:Langchain ai Langchain Vector Store Operations
- Workflow:Princeton nlp Tree of thought llm Adding new task
- Workflow:ChenghaoMou Text dedup Bloom Filter Deduplication
- Workflow:Apache Beam Dataflow Streaming Execution
- Workflow:OpenGVLab InternVL Supervised Finetuning
Principles
- Principle:FlowiseAI Flowise Chat Widget Embedding
- Principle:Huggingface Datatrove Unigram Log Probability Filtering
- Principle:Marker Inc Korea AutoRAG Evaluator Initialization
- Principle:Trailofbits Fickling Benchmark Payload Injection
- Principle:Dagster io Dagster Declarative Automation
- Principle:FMInference FlexLLMGen DeepSpeed Package Build
- Principle:Danijar Dreamerv3 Distributed Actor Inference
- Principle:Pytorch Serve Pipeline Parallelism
- Principle:Online ml River Built In Datasets
- Principle:CrewAIInc CrewAI Output Processing
Implementations
- Implementation:Openclaw Openclaw SetupChannels
- Implementation:Langgenius Dify RetrievalConfig Type
- Implementation:Recommenders team Recommenders Download Utils
- Implementation:Anthropics Anthropic sdk python JSON Output Format
- Implementation:Ollama Ollama Llama Memory Interface
- Implementation:Speechbrain Speechbrain Train IWSLT22 W2V mBART
- Implementation:Arize ai Phoenix Legacy AnthropicModel
- Implementation:Ucbepic Docetl Dataset Debate Baseline
- Implementation:Avhz RustQuant Linear Interpolation
- Implementation:Bentoml BentoML Gradio Mount
Heuristics
- Heuristic:Sail sg LongSpec Tree Shape Configuration
- Heuristic:Vibrantlabsai Ragas Reasoning Model Parameter Constraints
- Heuristic:Avhz RustQuant Interpolation Method Selection
- Heuristic:Testtimescaling Testtimescaling github io Dual JSON Sync
- Heuristic:Guardrails ai Guardrails Async Vs Sync Validation Mode
- Heuristic:Intel Ipex llm CCL Distributed Training Tips
- Heuristic:TA Lib Ta lib python Thread Safety With Abstract API
- Heuristic:Romsto Speculative Decoding Ngram Order Selection
- Heuristic:Duckdb Duckdb Build Parallelism Tuning
- Heuristic:Huggingface Transformers Gradient Checkpointing Memory Tradeoff
Environments
- Environment:Alibaba ROLL SGLang Inference Environment
- Environment:Junyanz Pytorch CycleGAN and pix2pix DDP Multi GPU
- Environment:Openai Openai python Realtime WebSocket
- Environment:Googleapis Python genai Python 3 10 SDK Runtime
- Environment:DevExpress Testcafe Node Runtime
- Environment:Google deepmind Dm control Python MuJoCo Runtime
- Environment:Huggingface Open r1 vLLM Server
- Environment:Gretelai Gretel synthetics TensorFlow GPU Environment
- Environment:Microsoft Playwright Platform Support Environment
- Environment:TobikoData Sqlmesh GitHub CICD Runner