Main Page
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:Vespa engine Vespa Document indexing pipeline
- Workflow:NVIDIA TransformerEngine Accelerate HF Gemma With TE
- Workflow:Openai Openai python Fine Tuning Job Management
- Workflow:Deepspeedai DeepSpeed Hybrid Engine RLHF Training
- Workflow:DataExpert io Data engineer handbook PySpark Job Testing
- Workflow:Googleapis Python genai Image Generation Pipeline
- Workflow:Onnx Onnx Version Conversion
- Workflow:FlagOpen FlagEmbedding Benchmark Evaluation
- Workflow:Deepset ai Haystack RAG Pipeline
- Workflow:Scikit learn Scikit learn Cross Validation Evaluation
Principles
- Principle:Ggml org Llama cpp Model Distribution
- Principle:Langgenius Dify Application Bootstrap
- Principle:Deepset ai Haystack Semantic Answer Similarity Evaluation
- Principle:TobikoData Sqlmesh Plan Confirmation And Application
- Principle:Huggingface Peft SFT Training
- Principle:Ggml org Llama cpp Benchmarking
- Principle:Langfuse Langfuse Export Job Creation
- Principle:Truera Trulens LangGraph Agent Construction
- Principle:Iterative Dvc Experiment Apply Or Discard
- Principle:Onnx Onnx External Data Conversion
Implementations
- Implementation:Promptfoo Promptfoo SharePoint Integration
- Implementation:Langfuse Langfuse CreatePrompt
- Implementation:Volcengine Verl GSM8K Data Preprocessing
- Implementation:Microsoft LoRA Run GLUE Evaluation
- Implementation:Vllm project Vllm Snapshot Download Draft
- Implementation:InternLM Lmdeploy DLPack
- Implementation:Helicone Helicone Filters
- Implementation:InternLM Lmdeploy State
- Implementation:Langchain ai Langgraph SDK Schema
- Implementation:Cohere ai Cohere python ChatSearchResult Model
Heuristics
- Heuristic:Mlc ai Web llm Multi Round KV Cache Reuse
- Heuristic:Marker Inc Korea AutoRAG Passage Filter Safety Minimum
- Heuristic:PeterL1n BackgroundMattingV2 Checkpoint Interval Tuning
- Heuristic:EvolvingLMMs Lab Lmms eval Request Caching Strategy
- Heuristic:Deepseek ai Janus Bfloat16 Dtype Selection
- Heuristic:Puppeteer Puppeteer Headless Linux Requirements
- Heuristic:Mlc ai Web llm Grammar Matcher Reuse
- Heuristic:Tencent Ncnn Vulkan Pipeline Warmup
- Heuristic:SeleniumHQ Selenium Thread Safety With ThreadGuard
- Heuristic:Dagster io Dagster Retry Strategy Configuration
Environments
- Environment:Spotify Luigi Tornado Web Server
- Environment:Alibaba MNN ARM Mobile Environment
- Environment:Unslothai Unsloth Python Transformers
- Environment:Allenai Open instruct Docker Container
- Environment:Mistralai Client python GCP Deployment Environment
- Environment:LMCache LMCache VLLM Serving Engine
- Environment:TA Lib Ta lib python TA Lib C Library
- Environment:Google research Deduplicate text datasets Rust Cargo Build Environment
- Environment:Rapidsai Cuml Dask Distributed
- Environment:Lance format Lance SIMD And Platform Requirements