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:Evidentlyai Evidently ML Model Quality Report
- Workflow:Cohere ai Cohere python Tool Use Agentic Chat
- Workflow:Huggingface Diffusers Model Quantization
- Workflow:Vespa engine Vespa Config subscription lifecycle
- Workflow:TA Lib Ta lib python Candlestick Pattern Recognition
- Workflow:Fede1024 Rust rdkafka At Least Once Processing
- Workflow:Open compass VLMEvalKit Adding Custom VLM
- Workflow:Apache Beam Dataflow Streaming Execution
- Workflow:Ggml org Ggml GPT2 Text Generation
- Workflow:AnswerDotAI RAGatouille In Memory Retrieval
Principles
- Principle:Wandb Weave Prompt Definition
- Principle:Bentoml BentoML Model Loading For Serving
- Principle:Protectai Llm guard API Application Factory
- Principle:NVIDIA NeMo Curator Video Ingestion
- Principle:NVIDIA NeMo Aligner RLHF Prompt Data Preparation
- Principle:Recommenders team Recommenders Stratified Data Splitting
- Principle:BerriAI Litellm Proxy Configuration
- Principle:Huggingface Datasets TF Dataset Creation
- Principle:Online ml River SNARIMAX Forecasting
- Principle:Intel Ipex llm Pipeline Parallel Init
Implementations
- Implementation:Hiyouga LLaMA Factory V1 CLI Sampler
- Implementation:ARISE Initiative Robosuite CheckCustomRobotModel
- Implementation:Cypress io Cypress SetupV8Snapshots
- Implementation:Vibrantlabsai Ragas EvaluationDataset From List
- Implementation:Trailofbits Fickling Pickled Load
- Implementation:Huggingface Datasets SparkDatasetReader
- Implementation:Microsoft Autogen Agbench Remove Missing Cmd
- Implementation:Huggingface Datatrove MinhashDedupBuckets
- Implementation:Spcl Graph of thoughts SortingParser
- Implementation:Huggingface Datasets Value
Heuristics
- Heuristic:Microsoft Agent framework Async Context Manager Cleanup
- Heuristic:Apache Shardingsphere DDL Refresher Superclass Fallback
- Heuristic:Allenai Open instruct Logprob Clamping
- Heuristic:Neuml Txtai Batch Size Defaults
- Heuristic:NVIDIA NeMo Curator Deduplication Blocksize Tuning
- Heuristic:Junyanz Pytorch CycleGAN and pix2pix Adam Beta1 Half
- Heuristic:Open compass VLMEvalKit SKIP ERR For Graceful Inference
- Heuristic:Apache Spark Serialization Optimization
- Heuristic:Haotian liu LLaVA Gradient Checkpointing Memory Optimization
- Heuristic:Scikit learn Scikit learn Working Memory Tuning
Environments
- Environment:Run llama Llama index OpenAI API Configuration
- Environment:Apache Druid Druid Operator Kubernetes
- Environment:Vllm project Vllm AWS ECR
- Environment:Eric mitchell Direct preference optimization PyTorch CUDA
- Environment:Vibrantlabsai Ragas Optional NLP Metrics Environment
- Environment:Datahub project Datahub Python Ingestion
- Environment:Tensorflow Serving Python Client Environment
- Environment:Neuml Txtai GPU Accelerator Environment
- Environment:Arize ai Phoenix Python Runtime
- Environment:FMInference FlexLLMGen CUDA GPU