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:ARISE Initiative Robosuite Human Demonstration Collection
- Workflow:Apache Hudi Flink Table Clustering
- Workflow:Intel Ipex llm DPO Finetuning
- Workflow:Cohere ai Cohere python Semantic Search With Rerank
- Workflow:Sail sg LongSpec GLIDE Draft Model Training
- Workflow:SeldonIO Seldon core HuggingFace Model Serving
- Workflow:Huggingface Transformers Model Quantization
- Workflow:Huggingface Optimum Accelerated Inference Pipeline
- Workflow:Apache Beam Local Pipeline Execution
- Workflow:Huggingface Diffusers Text to Image Inference
Principles
- Principle:Mlc ai Web llm Cosine Similarity Search
- Principle:Huggingface Datasets JSON Dataset Building
- Principle:Huggingface Datasets Spark Dataset Building
- Principle:Mlc ai Web llm Web Worker Engine Handler
- Principle:Explodinggradients Ragas Metric Baseline Correlation
- Principle:Anthropics Anthropic sdk python Streaming Thinking Content
- Principle:Apache Airflow Database Backend Configuration
- Principle:Openai Openai node Fine Tuning Job Creation
- Principle:Pyro ppl Pyro No U Turn Sampling
- Principle:Volcengine Verl VLM Actor Forward
Implementations
- Implementation:Ggml org Ggml Vulkan shader gen
- Implementation:NVIDIA NeMo Curator CaptionGenerationStage
- Implementation:ARISE Initiative Robosuite ConeObject
- Implementation:Deepspeedai DeepSpeed Inference Context
- Implementation:NVIDIA DALI PluginManager
- Implementation:Intel Ipex llm AutoModelForCausalLM From Pretrained PP
- Implementation:Langchain ai Langchain BaseChatModel Generate With Cache
- Implementation:Infiniflow Ragflow Http Client
- Implementation:OpenRLHF OpenRLHF Compute reward
- Implementation:MaterializeInc Materialize ResolvedImage Build
Heuristics
- Heuristic:Online ml River SNARIMAX Default Regressor Pipeline
- Heuristic:BerriAI Litellm Retry Backoff Strategy
- Heuristic:Marker Inc Korea AutoRAG Batch Size Tuning
- Heuristic:Open compass VLMEvalKit Video Frame Sampling Configuration
- Heuristic:Google research Deduplicate text datasets Parallel Job Scaling By Data Size
- Heuristic:Allenai Open instruct Gradient Clipping Norm
- Heuristic:Mbzuai oryx Awesome LLM Post training Checkpoint Every 3 Papers
- Heuristic:Microsoft LoRA Scaling Factor Alpha Over R
- Heuristic:Deepset ai Haystack Document Splitting Defaults
- Heuristic:ClickHouse ClickHouse Jemalloc Production Requirement
Environments
- Environment:Googleapis Python genai Gemini API Key Authentication
- Environment:OWASP Www project top 10 for large language model applications Pydantic Invoice Agent Runtime
- Environment:CarperAI Trlx Python Accelerate
- Environment:Diagram of thought Diagram of thought LLM API
- Environment:Bentoml BentoML NVIDIA GPU Resource
- Environment:Arize ai Phoenix LLM Provider SDKs
- Environment:Huggingface Peft Python Core Dependencies
- Environment:Lance format Lance Cloud Storage Credentials
- Environment:Kubeflow Pipelines Kubernetes Cluster
- Environment:DataTalksClub Data engineering zoomcamp Dbt DuckDB Environment