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:PacktPublishing LLM Engineers Handbook LLM Finetuning
- Workflow:LLMBook zh LLMBook zh github io LLM Pretraining
- Workflow:Kserve Kserve Deploying InferenceService
- Workflow:Onnx Onnx Model Composition
- Workflow:Onnx Onnx Model Validation
- Workflow:Mlc ai Web llm Text Embeddings And RAG
- Workflow:Apache Kafka PR Merge And Backport
- Workflow:Cohere ai Cohere python Streaming Chat
- Workflow:Unstructured IO Unstructured Performance Profiling
- Workflow:Huggingface Trl GRPO Training
Principles
- Principle:Apache Shardingsphere Persistence Facade Construction
- Principle:NVIDIA NeMo Curator MinHash Signature Computation
- Principle:Bentoml BentoML Bento Building
- Principle:Hpcaitech ColossalAI SFT Model Loading
- Principle:Mage ai Mage ai Incremental Sync State
- Principle:Ggml org Llama cpp Token Sampling
- Principle:Huggingface Datatrove Language Identification
- Principle:Rapidsai Cuml Cluster Model Fitting
- Principle:Microsoft Agent framework Edge Condition Pattern
- Principle:Cypress io Cypress Browser Test Execution
Implementations
- Implementation:Interpretml Interpret Process Terms
- Implementation:OWASP Www project top 10 for large language model applications VulnerabilityEntry Parse Sections
- Implementation:Ggml org Llama cpp Arch Registry
- Implementation:Dagster io Dagster Dagster Pipes Client
- Implementation:Facebookresearch Audiocraft CompressionSolver run step
- Implementation:Fede1024 Rust rdkafka MockCluster Create Topic
- Implementation:Deepset ai Haystack MetadataRouter
- Implementation:Microsoft DeepSpeedExamples BingBert NvidiaPreLN LayerDrop
- Implementation:Openai Openai python Shared Compound Filter
- Implementation:Vllm project Vllm Benchmark Serving Structured Output
Heuristics
- Heuristic:Pytorch Serve Ampere Tensor Core Optimization
- Heuristic:Princeton nlp Tree of thought llm Duplicate Candidate Zeroing
- Heuristic:Groq Groq python Streaming Usage Stats
- Heuristic:Cohere ai Cohere python ToolCallV2 Auto UUID Override
- Heuristic:Kserve Kserve Server Side Apply For CRDs
- Heuristic:Openai Openai node RunTools Loop Limit
- Heuristic:DevExpress Testcafe Video Encoding Defaults
- Heuristic:DataExpert io Data engineer handbook SparkSession Singleton Pattern
- Heuristic:Norrrrrrr lyn WAInjectBench Union Ensemble Maximize Recall
- Heuristic:Microsoft BIPIA LLAMA Pad Token Workaround
Environments
- Environment:Princeton nlp SimPO VLLM Inference
- Environment:Shiyu coder Kronos PyTorch CUDA Environment
- Environment:Microsoft Autogen LLM Provider API Keys
- Environment:NVIDIA NeMo Aligner TensorRT LLM Acceleration Environment
- Environment:Eventual Inc Daft AI Provider Dependencies
- Environment:Bitsandbytes foundation Bitsandbytes Build From Source Environment
- Environment:CrewAIInc CrewAI LLM Provider Credentials
- Environment:Langchain ai Langchain LangSmith Tracing Config
- Environment:Datahub project Datahub Docker Runtime
- Environment:Haotian liu LLaVA Python CUDA Training Environment