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:Groq Groq python Batch Processing
- Workflow:Openai Openai python Realtime Conversation
- Workflow:Romsto Speculative Decoding Ngram Assisted Speculative Decoding
- Workflow:Lm sys FastChat Distributed Model Serving
- Workflow:Sdv dev SDV Multi table synthesis
- Workflow:Spcl Graph of thoughts Custom GoT Use Case Integration
- Workflow:Apache Airflow Provider Distribution Development
- Workflow:AUTOMATIC1111 Stable diffusion webui Checkpoint merging
- Workflow:Apache Paimon Blob Storage With Descriptors
- Workflow:Arize ai Phoenix Trace Ingestion Pipeline
Principles
- Principle:CarperAI Trlx Synthetic Environment Design
- Principle:DistrictDataLabs Yellowbrick Feature Dropping Analysis
- Principle:Ollama Ollama ChatTemplate
- Principle:Apache Kafka Topic CLI Bootstrap
- Principle:Getgauge Taiko Gauge Project Setup
- Principle:Apache Flink Data Generation
- Principle:AUTOMATIC1111 Stable diffusion webui VAE decoding and output composition
- Principle:Lance format Lance Data Ingestion
- Principle:Norrrrrrr lyn WAInjectBench Per Folder Image Detection
- Principle:ClickHouse ClickHouse Package Validation
Implementations
- Implementation:CrewAIInc CrewAI RAG XML Loader
- Implementation:Google deepmind Mujoco Filament Builtins
- Implementation:Tensorflow Tfjs Recurrent Layers
- Implementation:ClickHouse ClickHouse Musl Log Data
- Implementation:Astronomer Astronomer cosmos DbtVirtualenvBaseOperator
- Implementation:CARLA simulator Carla ConstantVelocityAgent
- Implementation:NVIDIA NeMo Curator Wikipedia Iterator
- Implementation:CrewAIInc CrewAI MongoDB Vector Search Tool
- Implementation:Google deepmind Mujoco Filament Context
- Implementation:Infiniflow Ragflow MetadataManageValuesModal Component
Heuristics
- Heuristic:NVIDIA NeMo Aligner Warning Deprecated Repository
- Heuristic:Bitsandbytes foundation Bitsandbytes CuBLAS Int8 Dimension Alignment
- Heuristic:Fede1024 Rust rdkafka Regular Polling Required
- Heuristic:Mlc ai Mlc llm BLAS Dispatch Decision
- Heuristic:Apache Druid Capability Detection Strategy
- Heuristic:Huggingface Alignment handbook Gradient Checkpointing Use Cache
- Heuristic:Huggingface Open r1 Test Batch Early Termination
- Heuristic:EvolvingLMMs Lab Lmms eval Request Caching Strategy
- Heuristic:ThreeSR Awesome Inference Time Scaling Duplicate Detection By Title
- Heuristic:Iamhankai Forest of Thought UCB Exploration Constant
Environments
- Environment:Huggingface Transformers Flash Attention 2 Env
- Environment:Guardrails ai Guardrails Docker Server Runtime
- Environment:SeldonIO Seldon core Kafka Messaging Environment
- Environment:Vllm project Vllm CUDA GPU Runtime
- Environment:Risingwavelabs Risingwave Java Connector Environment
- Environment:Vllm project Vllm CUDA Runtime
- Environment:Kubeflow Kubeflow Istio Certmanager Dex Environment
- Environment:Heibaiying BigData Notes Kafka 2 2 Environment
- Environment:SeldonIO Seldon core GPU Inference Environment
- Environment:Facebookresearch Habitat lab CUDA GPU Training Environment