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:Helicone Helicone Cost Calculation Pipeline
- Workflow:Cleanlab Cleanlab Token Classification Label Quality
- Workflow:Apache Druid Batch Data Ingestion
- Workflow:Cohere ai Cohere python Tool Use Agentic Chat
- Workflow:Duckdb Duckdb Building From Source
- Workflow:PacktPublishing LLM Engineers Handbook Feature Engineering
- Workflow:Guardrails ai Guardrails Streaming Validation
- Workflow:Openclaw Openclaw Initial Setup And Onboarding
- Workflow:Cohere ai Cohere python Text Embedding
- Workflow:Apache Hudi Flink Schema Evolution
Principles
- Principle:Ggml org Llama cpp Chat Model Initialization
- Principle:Huggingface Peft Adapter Injection
- Principle:Princeton nlp Tree of thought llm Thought Evaluation
- Principle:Huggingface Datatrove Tokenizer Loading
- Principle:Tensorflow Tfjs BPE Tokenization
- Principle:Pyro ppl Pyro Deterministic Computation
- Principle:Unslothai Unsloth Response Masking
- Principle:Togethercomputer Together python Batch Job Creation
- Principle:DistrictDataLabs Yellowbrick RadViz Visualization
- Principle:Treeverse LakeFS Diff and Review
Implementations
- Implementation:Nautechsystems Nautilus trader Order Position Handlers
- Implementation:Microsoft Onnxruntime CUDA GatherGrad
- Implementation:Neuml Txtai Similarity
- Implementation:AUTOMATIC1111 Stable diffusion webui XLMRoBERTa Encoder
- Implementation:Openai Openai node Beta Realtime TranscriptionSessions
- Implementation:ARISE Initiative Robosuite Robotiq85Gripper
- Implementation:ARISE Initiative Robosuite HumanoidModel
- Implementation:Dagster io Dagster AutomationCondition API
- Implementation:Haifengl Smile Spatial Index Constructors
- Implementation:BerriAI Litellm CircleCI Config
Heuristics
- Heuristic:Intel Ipex llm CCL Distributed Training Tips
- Heuristic:Huggingface Datasets Warning Deprecated Pandas Builder
- Heuristic:Explodinggradients Ragas Failed Metrics Return NaN
- Heuristic:Openai Openai python Timeout Connection Defaults
- Heuristic:DataTalksClub Data engineering zoomcamp DuckDB OOM Memory Management
- Heuristic:Volcengine Verl Sequence Length Balancing
- Heuristic:TobikoData Sqlmesh Snapshot TTL Defaults
- Heuristic:Fastai Fastbook Learning Rate Finder Rule
- Heuristic:Vibrantlabsai Ragas Warning Deprecated Legacy LLM Wrappers
- Heuristic:Triton inference server Server Server Default Configuration
Environments
- Environment:CarperAI Trlx Python Accelerate
- Environment:Heibaiying BigData Notes Hadoop CDH Environment
- Environment:CARLA simulator Carla Build From Source Requirements
- Environment:Unstructured IO Unstructured GitHub Actions
- Environment:Marker Inc Korea AutoRAG Korean NLP Dependencies
- Environment:Apache Shardingsphere Java Runtime Environment
- Environment:Risingwavelabs Risingwave Python Tooling Environment
- Environment:Nautechsystems Nautilus trader Python Cython Rust Runtime
- Environment:Mlfoundations Open flamingo HuggingFace Open CLIP Dependencies
- Environment:Mbzuai oryx Awesome LLM Post training Python Pandas