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:Open compass VLMEvalKit Image Benchmark Evaluation
- Workflow:Turboderp org Exllamav2 Bulk Dataset Inference
- Workflow:SeldonIO Seldon core Inference Pipeline
- Workflow:Togethercomputer Together python Batch Inference
- Workflow:OWASP Www project top 10 for large language model applications LLM Vulnerability Assessment
- Workflow:Cypress io Cypress Component Test Execution
- Workflow:Bentoml BentoML Model Store Management
- Workflow:Togethercomputer Together python Image Generation
- Workflow:Confident ai Deepeval End to End LLM Evaluation
- Workflow:Tencent Ncnn Vulkan GPU Accelerated Inference
Principles
- Principle:LMCache LMCache CacheBlend Configuration
- Principle:Langgenius Dify React Query Pattern
- Principle:Guardrails ai Guardrails Stream Invocation
- Principle:LaurentMazare Tch rs Transposed Convolution
- Principle:Liu00222 Open Prompt Injection Input Preprocessing
- Principle:Wandb Weave Prompt Publishing
- Principle:ArroyoSystems Arroyo Connection Table Configuration
- Principle:Huggingface Transformers Pipeline Instantiation
- Principle:Langgenius Dify Model Configuration
- Principle:Cohere ai Cohere python Input Text Preparation
Implementations
- Implementation:FlowiseAI Flowise MultiDropdown
- Implementation:OpenGVLab InternVL LLaMA Flash Attention Patch
- Implementation:Triton inference server Server Tritonclient Infer
- Implementation:Microsoft Onnxruntime CPU DropoutGrad
- Implementation:Risingwavelabs Risingwave StreamChunk
- Implementation:ClickHouse ClickHouse Clickhouse Client Health Check
- Implementation:ClickHouse ClickHouse Clickhouse Server Start
- Implementation:Scikit learn contrib Imbalanced learn RUSBoostClassifier
- Implementation:PrefectHQ Prefect Asset Constructor
- Implementation:Apache Paimon BlobDescriptor Create and Serialize
Heuristics
- Heuristic:Online ml River HST Feature Scaling Requirement
- Heuristic:OpenHands OpenHands Clustered Race Condition Prevention
- Heuristic:Scikit learn Scikit learn N Jobs Parallelism Tips
- Heuristic:Huggingface Open r1 Code Execution Timeout Strategy
- Heuristic:Apache Hudi Data Skipping Limitations
- Heuristic:Sdv dev SDV Sampling Retry Tuning
- Heuristic:LaurentMazare Tch rs Device Fallback Pattern
- Heuristic:Microsoft Semantic kernel Telemetry Log Level Configuration
- Heuristic:FMInference FlexLLMGen Weight Compression 4bit
- Heuristic:Deepspeedai DeepSpeed Vocabulary Tensor Core Alignment
Environments
- Environment:Apache Shardingsphere Etcd Cluster Coordination
- Environment:OpenBMB UltraFeedback OpenAI API Environment
- Environment:Online ml River Python Runtime Environment
- Environment:Volcengine Verl Ray Distributed Environment
- Environment:Google deepmind Dm control GLFW Desktop Rendering
- Environment:LLMBook zh LLMBook zh github io PyTorch CUDA GPU Environment
- Environment:Truera Trulens Python Core Environment
- Environment:Wandb Weave LLM Integration Dependencies
- Environment:Duckdb Duckdb Code Generation Tools
- Environment:Sgl project Sglang Triton