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:Predibase Lorax Multi Adapter Merging
- Workflow:Vllm project Vllm OpenAI Compatible Serving
- Workflow:Triton inference server Server Model Performance Tuning
- Workflow:Huggingface Diffusers Video Generation
- Workflow:Testtimescaling Testtimescaling github io GitHub Pages Course Progression
- Workflow:Huggingface Open r1 Model Evaluation
- Workflow:Huggingface Datatrove Common Crawl Processing
- Workflow:Mlflow Mlflow Experiment Tracking
- Workflow:Vespa engine Vespa Linguistics text processing pipeline
- Workflow:Kserve Kserve Multi Model Serving
Principles
- Principle:Protectai Llm guard Prompt Scanning
- Principle:Ggml org Llama cpp Draft Model Loading
- Principle:FMInference FlexLLMGen Autotuning Experiment Scheduling
- Principle:Puppeteer Puppeteer PDF Generation
- Principle:Huggingface Datatrove Text Encoding Repair
- Principle:Sdv dev SDV Inequality Constraint
- Principle:Infiniflow Ragflow Infrastructure Orchestration
- Principle:Evidentlyai Evidently LLM Judge Evaluation
- Principle:Turboderp org Exllamav2 KV Cache Allocation
- Principle:ThreeSR Awesome Inference Time Scaling Readme Merge And Sort
Implementations
- Implementation:TobikoData Sqlmesh Tracker Plan Apply
- Implementation:Tencent Ncnn YOLOv4 Example
- Implementation:Apache Flink Pool
- Implementation:Online ml River Anomaly ThresholdFilter
- Implementation:Farama Foundation Gymnasium ArrayConversion
- Implementation:Microsoft Playwright BidiSerializer
- Implementation:Langchain ai Langgraph AsyncPostgresStore
- Implementation:ContextualAI HALOs Online Loop Script
- Implementation:Vllm project Vllm SamplingParams Init
- Implementation:NVIDIA TransformerEngine Llama Replace Params
Heuristics
- Heuristic:Langgenius Dify SQL Escape Backslash First
- Heuristic:Huggingface Datasets Warning Deprecated Pandas Builder
- Heuristic:VainF Torch Pruning GQA Head Pruning Constraints
- Heuristic:Ggml org Llama cpp Quantization Quality Tips
- Heuristic:Bitsandbytes foundation Bitsandbytes Blocksize Platform Defaults
- Heuristic:LMCache LMCache Chunk Size And Default Config
- Heuristic:Deepset ai Haystack BM25 Score Scaling
- Heuristic:Mlfoundations Open flamingo Loss Masking Strategy
- Heuristic:Mage ai Mage ai Sorted Data Bookmark Strategy
- Heuristic:ClickHouse ClickHouse Banned Functions Thread Safety
Environments
- Environment:Neuml Txtai API Server Configuration
- Environment:Scikit learn Scikit learn OpenMP Thread Configuration
- Environment:Datahub project Datahub Python Ingestion
- Environment:Cypress io Cypress Node Runtime Environment
- Environment:Protectai Modelscan Python Core Runtime
- Environment:Langfuse Langfuse S3 Compatible Storage
- Environment:Sgl project Sglang Distributed
- Environment:Langfuse Langfuse ClickHouse Analytics
- Environment:Explodinggradients Ragas Optional Metrics Environment
- Environment:Tencent Ncnn PyTorch Environment