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:Wandb Weave LLM Integration Tracing
- Workflow:Mlfoundations Open flamingo Few Shot Evaluation
- Workflow:Nightwatchjs Nightwatch Custom Commands And Assertions
- Workflow:Obss Sahi COCO Dataset Slicing
- Workflow:Pyro ppl Pyro Bayesian Regression
- Workflow:Anthropics Anthropic sdk python Basic Message Conversation
- Workflow:Ollama Ollama Model Registry Operations
- Workflow:Princeton nlp SimPO On Policy Data Generation
- Workflow:CrewAIInc CrewAI Sequential Crew Execution
- Workflow:DataTalksClub Data engineering zoomcamp Spark Batch Processing
Principles
- Principle:Confident ai Deepeval Golden Generation from Documents
- Principle:NVIDIA NeMo Aligner DPO Reference Policy Management
- Principle:Vllm project Vllm Multimodal Output Processing
- Principle:ClickHouse ClickHouse SIMD Memory Comparison
- Principle:Huggingface Datatrove Megatron Format Tokenization
- Principle:Princeton nlp Tree of thought llm Prompt Engineering
- Principle:Webdriverio Webdriverio WebDriver Bidi Protocol
- Principle:Cleanlab Cleanlab Multilabel Quality Scoring
- Principle:AUTOMATIC1111 Stable diffusion webui Network weight patching
- Principle:Apache Kafka Maven Artifact Publishing
Implementations
- Implementation:NVIDIA DALI PluginManager
- Implementation:FlagOpen FlagEmbedding FlagAutoReranker From Finetuned Validation
- Implementation:Diagram of thought Diagram of thought Format Compliance Validator
- Implementation:Shiyu coder Kronos KronosTokenizer From Pretrained
- Implementation:Apache Flink AsyncDynamicTableSinkBuilder
- Implementation:Isaac sim IsaacGymEnvs Runner Play Mode
- Implementation:Elevenlabs Elevenlabs python Voice Model
- Implementation:CrewAIInc CrewAI Crew Replay Method
- Implementation:BerriAI Litellm Check Responses Cost
- Implementation:Intel Ipex llm AutoModelForCausalLM From Pretrained PP
Heuristics
- Heuristic:CARLA simulator Carla Walker Spawn Vertical Offset
- Heuristic:Langchain ai Langgraph Recursion Limit Tuning
- Heuristic:OpenRLHF OpenRLHF Adam Offload Memory Tip
- Heuristic:Huggingface Datasets Parquet Shard Sizing
- Heuristic:Norrrrrrr lyn WAInjectBench LoRA Rank Alpha Selection
- Heuristic:Apache Spark Build Fallback Strategies
- Heuristic:Onnx Onnx Warning Deprecated InlineSelectedFunctions
- Heuristic:Facebookresearch Audiocraft Codebook Dead Code Expiration
- Heuristic:Mlflow Mlflow Async Logging Best Practices
- Heuristic:EvolvingLMMs Lab Lmms eval Memory Cleanup After Inference
Environments
- Environment:Snorkel team Snorkel PyTorch
- Environment:ThreeSR Awesome Inference Time Scaling Semantic Scholar API Environment
- Environment:BerriAI Litellm Provider API Credentials
- Environment:Microsoft BIPIA Python CUDA GPU Environment
- Environment:Vllm project Vllm NVIDIA CUDA
- Environment:Microsoft Agent framework API Credentials
- Environment:SeldonIO Seldon core Go Build Toolchain Environment
- Environment:Microsoft Autogen LLM Provider API Keys
- Environment:Mlc ai Mlc llm OpenCL Android Environment
- Environment:Kubeflow Pipelines KFP Backend Deployment