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:Facebookresearch Audiocraft MusicGen Text To Music Inference
- Workflow:EvolvingLMMs Lab Lmms eval Custom Model Integration
- Workflow:Google deepmind Mujoco GPU batched simulation MJX
- Workflow:Duckdb Duckdb Source Amalgamation And Packaging
- Workflow:Avhz RustQuant Yield Curve Construction
- Workflow:Heibaiying BigData Notes Storm Topology Development
- Workflow:Apache Beam Portable Pipeline Submission
- Workflow:Mlfoundations Open flamingo Model Creation And Inference
- Workflow:Predibase Lorax Multi Adapter Merging
- Workflow:DevExpress Testcafe CLI Test Execution
Principles
- Principle:Datajuicer Data juicer Operator Fusion
- Principle:Mit han lab Llm awq LM Evaluation Harness Adaptation
- Principle:Nightwatchjs Nightwatch Dependency Management
- Principle:Helicone Helicone Model Provider Identification
- Principle:Vespa engine Vespa Embedding Generation
- Principle:LLMBook zh LLMBook zh github io Pretraining Dataset Preparation
- Principle:Cohere ai Cohere python Finetuned Model Creation
- Principle:Danijar Dreamerv3 Environment Construction
- Principle:Tensorflow Serving Servable Access Pattern
- Principle:MarketSquare Robotframework browser Code Quality Enforcement
Implementations
- Implementation:Kserve Kserve Batcher Sample Input
- Implementation:NVIDIA NeMo Curator IDGenerator
- Implementation:Openai Openai python Response Model
- Implementation:Infiniflow Ragflow Agent Constants
- Implementation:Huggingface Datatrove MinhashDedupBuckets
- Implementation:Lance format Lance RepDef
- Implementation:Diagram of thought Diagram of thought Proposer Critic XML Cycle
- Implementation:CrewAIInc CrewAI Crew Kickoff
- Implementation:Huggingface Diffusers DiffusersAutoQuantizer From Config
- Implementation:Sgl project Sglang LLaVA Video Pipeline
Heuristics
- Heuristic:BerriAI Litellm Token Counting Buffer
- Heuristic:Haotian liu LLaVA Use Cache Training Inference Toggle
- Heuristic:Google research Deduplicate text datasets Parallel Job Scaling By Data Size
- Heuristic:Explodinggradients Ragas Retry And Backoff Configuration
- Heuristic:Mbzuai oryx Awesome LLM Post training Reference Citation Cap 200
- Heuristic:Huggingface Datatrove FineWeb Filter Pipeline Order
- Heuristic:Deepseek ai Janus Image Generation Prompt Tips
- Heuristic:Open compass VLMEvalKit Judge Model Selection By Dataset
- Heuristic:Deepseek ai Janus Bfloat16 Operation Workarounds
- Heuristic:CarperAI Trlx Partial Layer Freezing
Environments
- Environment:Openai Openai agents python Voice Dependencies
- Environment:OpenHands OpenHands SaaS Server Environment
- Environment:Apache Kafka Docker Build Environment
- Environment:Dotnet Machinelearning OneDal Acceleration
- Environment:Cleanlab Cleanlab Datalab Dependencies
- Environment:Confident ai Deepeval Python 3 9 Runtime
- Environment:Allenai Open instruct Ray Distributed
- Environment:NVIDIA NeMo Aligner TensorRT LLM Acceleration Environment
- Environment:Anthropics Anthropic sdk python AWS Bedrock Environment
- Environment:Sgl project Sglang Multimodal