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:Langfuse Langfuse Dataset experiment pipeline
- Workflow:Datahub project Datahub Protobuf Schema Ingestion
- Workflow:Guardrails ai Guardrails Streaming Validation
- Workflow:ChenghaoMou Text dedup Suffix Array Deduplication
- Workflow:OWASP Www project top 10 for large language model applications LLM Vulnerability Assessment
- Workflow:Danijar Dreamerv3 Evaluation Only
- Workflow:ContextualAI HALOs Online Iterative Alignment
- Workflow:Dagster io Dagster ETL Pipeline
- Workflow:Neuml Txtai Pipeline Workflow Chaining
- Workflow:Microsoft LoRA NLU GLUE Finetuning
Principles
- Principle:Deepspeedai DeepSpeed Tensor Parallel Training
- Principle:Openai Openai python Chat Response Processing
- Principle:LMCache LMCache NIXL KV Transfer
- Principle:Zai org CogVideo Activation Normalization
- Principle:DevExpress Testcafe CDP Browser Control
- Principle:Openai Openai agents python Computer Use
- Principle:Kubeflow Kubeflow Pull Request Submission
- Principle:Duckdb Duckdb Release Artifact Upload
- Principle:Langgenius Dify Frontend Architecture
- Principle:CARLA simulator Carla Actor Spawning
Implementations
- Implementation:Princeton nlp SimPO Conda Environment Create
- Implementation:Spcl Graph of thoughts Llama2HF
- Implementation:Mage ai Mage ai Source Write Records
- Implementation:Openai Openai python SDK Package Exports
- Implementation:Microsoft LoRA Hubconf
- Implementation:ARISE Initiative Robosuite Robot Create Action Vector
- Implementation:Open compass VLMEvalKit SArena Inception
- Implementation:Astronomer Astronomer cosmos Task Dependency Wiring
- Implementation:DevExpress Testcafe CLI Run Orchestration
- Implementation:Evidentlyai Evidently SDK Models
Heuristics
- Heuristic:Anthropics Anthropic sdk python Retry Backoff Strategy
- Heuristic:Deepseek ai Janus CFG Weight Tuning
- Heuristic:Romsto Speculative Decoding Gamma Tuning
- Heuristic:Openai CLIP CLIP Normalization Constants
- Heuristic:Fastai Fastbook Mixup Data Augmentation
- Heuristic:Datahub project Datahub Secret Handling And Deprecation Patterns
- Heuristic:Scikit learn contrib Imbalanced learn Sampling Before Split Leakage
- Heuristic:Bitsandbytes foundation Bitsandbytes Outlier Threshold Detection
- Heuristic:Gretelai Gretel synthetics Mixed Precision Training Tradeoff
- Heuristic:Obss Sahi Class Agnostic vs Per Class NMS
Environments
- Environment:LMCache LMCache VLLM Serving Engine
- Environment:Unstructured IO Unstructured Profiling Tools
- Environment:Hiyouga LLaMA Factory Optional Inference Backends
- Environment:Vllm project Vllm GitHub
- Environment:PacktPublishing LLM Engineers Handbook API Credentials
- Environment:Eventual Inc Daft Ray Distributed Runner
- Environment:Diagram of thought Diagram of thought LLM API
- Environment:DataTalksClub Data engineering zoomcamp Kafka Confluent Environment
- Environment:OpenBMB UltraFeedback OpenAI API Environment
- Environment:FMInference FlexLLMGen HuggingFace Access