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:Romsto Speculative Decoding Speculative Decoding Inference
- Workflow:FlowiseAI Flowise Chatflow Creation
- Workflow:Apache Druid SQL Query Execution
- Workflow:FlagOpen FlagEmbedding Reranker Inference
- Workflow:SeleniumHQ Selenium Selenium Grid Deployment
- Workflow:Wandb Weave Prompt Management
- Workflow:Apache Spark Kubernetes Deployment
- Workflow:Recommenders team Recommenders Algorithm Benchmarking
- Workflow:Webdriverio Webdriverio Cucumber BDD Testing
- Workflow:Ggml org Ggml MNIST Training And Evaluation
Principles
- Principle:Puppeteer Puppeteer Device Emulation
- Principle:Cohere ai Cohere python Stream Aggregation
- Principle:Run llama Llama index Embedding Finetune Configuration
- Principle:Spcl Graph of thoughts Thought State Management
- Principle:Apache Flink Compaction Request Triggering
- Principle:ChenghaoMou Text dedup Jaccard Similarity
- Principle:Webdriverio Webdriverio Configuration Constants
- Principle:Truera Trulens Feedback Result Retrieval
- Principle:PrefectHQ Prefect Structured AI Output
- Principle:Diagram of thought Diagram of thought Raw Output Collection
Implementations
- Implementation:Apache Flink HybridSource Builder
- Implementation:Pytorch Serve Accelerate Handler
- Implementation:Ggml org Llama cpp Memory Hybrid ISWA Header
- Implementation:Infiniflow Ragflow Parser Config Utils
- Implementation:FlowiseAI Flowise AllowedDomains
- Implementation:Mlflow Mlflow Exceptions
- Implementation:Ucbepic Docetl Blocking Utils
- Implementation:Run llama Llama index SemanticSimilarityEvaluator
- Implementation:Bentoml BentoML Runner Utils
- Implementation:CrewAIInc CrewAI TXT Search Tool
Heuristics
- Heuristic:Nautechsystems Nautilus trader Strategy On Start Initialization
- Heuristic:Groq Groq python Timeout Configuration
- Heuristic:Microsoft BIPIA LLAMA Pad Token Workaround
- Heuristic:VainF Torch Pruning Over Pruning Prevention
- Heuristic:EvolvingLMMs Lab Lmms eval Memory Cleanup After Inference
- Heuristic:Avhz RustQuant Learning Rate Tuning
- Heuristic:Webdriverio Webdriverio Stale Element Auto Refetch
- Heuristic:ArroyoSystems Arroyo Async UDF Concurrency
- Heuristic:Mbzuai oryx Awesome LLM Post training Excel Sheet Name Truncation
- Heuristic:OpenBMB UltraFeedback GPU Memory Utilization
Environments
- Environment:Protectai Modelscan H5py Optional
- Environment:Deepset ai Haystack Python Runtime Environment
- Environment:Ggml org Llama cpp Python Conversion Environment
- Environment:Mlfoundations Open flamingo Evaluation Dependencies
- Environment:Langgenius Dify Docker Deployment Environment
- Environment:Risingwavelabs Risingwave Docker Deployment Environment
- Environment:Avdvg InjectGuard CUDA GPU
- Environment:CrewAIInc CrewAI LLM Provider Credentials
- Environment:InternLM Lmdeploy Python Dependencies
- Environment:Kornia Kornia PyTorch Python Environment