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:Nautechsystems Nautilus trader Backtest with BacktestEngine
- Workflow:Lakeraai Pint benchmark Hugging Face Model Evaluation
- Workflow:Facebookresearch Habitat lab Rearrangement HRL Training
- Workflow:Groq Groq python Streaming Chat Completion
- Workflow:Spcl Graph of thoughts GoT Sorting Pipeline
- Workflow:Mistralai Client python Streaming Chat Completion
- Workflow:Trailofbits Fickling PyTorch Payload Injection
- Workflow:Mit han lab Llm awq HuggingFace Model Export
- Workflow:Vibrantlabsai Ragas Prompt Optimization
- Workflow:Cleanlab Cleanlab CleanLearning Robust Training
Principles
- Principle:Rapidsai Cuml Multiclass Classification Strategy
- Principle:Ggml org Llama cpp Chat Message Parsing
- Principle:Spotify Luigi HPC Batch Execution
- Principle:Huggingface Transformers Modular Model Architecture
- Principle:Neuml Txtai Content Conversion
- Principle:Getgauge Taiko Page Navigation
- Principle:Helicone Helicone Database Schema
- Principle:Deepseek ai Janus Autoregressive VQ Token Generation
- Principle:Recommenders team Recommenders Spark Session Management
- Principle:Huggingface Datatrove Random Sampling
Implementations
- Implementation:Microsoft Playwright Root Package Lock
- Implementation:Langchain ai Langchain Anthropic Prompt Caching
- Implementation:SqueezeAILab ETS Evaluate And Majority Vote
- Implementation:Pyro ppl Pyro VelocityVerlet
- Implementation:Eric mitchell Direct preference optimization Tokenize Batch Element
- Implementation:Bentoml BentoML Nerdctl Backend
- Implementation:Openai Openai python Response Image Gen Call Generating
- Implementation:Vespa engine Vespa KStemmer Stem
- Implementation:Huggingface Diffusers PipelineQuantizationConfig
- Implementation:NVIDIA NeMo Curator ImageNSFWFilterStage
Heuristics
- Heuristic:Fede1024 Rust rdkafka Regular Polling Required
- Heuristic:Sgl project Sglang Attention Backend Selection
- Heuristic:Iamhankai Forest of Thought Input Length Overflow Recovery
- Heuristic:Confident ai Deepeval Timeout and Retry Tuning
- Heuristic:Helicone Helicone Tiered Pricing Threshold Matching
- Heuristic:Pytorch Serve Ampere Tensor Core Optimization
- Heuristic:Dagster io Dagster Lazy Import Pattern
- Heuristic:Eric mitchell Direct preference optimization FSDP Mixed Precision BFloat16
- Heuristic:Open compass VLMEvalKit Judge Model Selection By Dataset
- Heuristic:PeterL1n BackgroundMattingV2 Checkpoint Interval Tuning
Environments
- Environment:Lance format Lance Rust Toolchain
- Environment:Googleapis Python genai Python 3 10 SDK Runtime
- Environment:Apache Druid Integration Test Docker
- Environment:Norrrrrrr lyn WAInjectBench OpenAI API Credentials
- Environment:Apache Flink Java Build Environment
- Environment:SeldonIO Seldon core Docker Compose Local Environment
- Environment:Predibase Lorax CUDA GPU Runtime
- Environment:Apache Airflow Python Runtime Environment
- Environment:OpenHands OpenHands SaaS Server Environment
- Environment:Ggml org Ggml Metal GPU Environment