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:Unslothai Unsloth Vision Model Finetuning
- Workflow:Marker Inc Korea AutoRAG Pipeline Deployment
- Workflow:CarperAI Trlx ILQL Offline Training
- Workflow:Microsoft Playwright Browser automation CLI
- Workflow:Wandb Weave Evaluation Pipeline
- Workflow:Run llama Llama index ReAct Agent
- Workflow:Onnx Onnx Model Validation
- Workflow:TobikoData Sqlmesh Dbt project migration
- Workflow:Mlc ai Mlc llm REST API Serving
- Workflow:Open compass VLMEvalKit API Model Evaluation
Principles
- Principle:LaurentMazare Tch rs SGD Optimization
- Principle:Apache Beam Worker Initialization
- Principle:Apache Spark Build Environment Setup
- Principle:Risingwavelabs Risingwave Iceberg Catalog Operations
- Principle:Mlc ai Web llm Structured Output Parsing
- Principle:Nightwatchjs Nightwatch BDD Style Expect Assertions
- Principle:Mlc ai Mlc llm Prefill Decode Disaggregation
- Principle:Marker Inc Korea AutoRAG Corpus Ingestion
- Principle:Sktime Pytorch forecasting Validation Dataset Creation
- Principle:Kserve Kserve Canary Validation
Implementations
- Implementation:Apache Shardingsphere ClusterMetaDataManagerPersistService AlterRuleConfiguration
- Implementation:FlagOpen FlagEmbedding VideoChat2 Choice Bench
- Implementation:Langfuse Langfuse BatchExportRouter Create
- Implementation:Kornia Kornia Super Resolution
- Implementation:FlagOpen FlagEmbedding Sentence Pair Construction
- Implementation:Openai Openai python Response Prompt Param
- Implementation:Openai Whisper BasicTextNormalizer
- Implementation:Pyro ppl Pyro MaternKernel
- Implementation:Junyanz Pytorch CycleGAN and pix2pix Download Dataset
- Implementation:ClickHouse ClickHouse Poco RemoteSyslogChannel
Heuristics
- Heuristic:Run llama Llama index Chunk Size Optimization
- Heuristic:Apache Druid Auto Granularity Selection
- Heuristic:Zai org CogVideo BF16 FP16 Precision Selection
- Heuristic:Dotnet Machinelearning Text File Sampling Strategy
- Heuristic:DevExpress Testcafe Video Encoding Defaults
- Heuristic:InternLM Lmdeploy Backend Selection Strategy
- Heuristic:Hiyouga LLaMA Factory LoRA DDP Configuration
- Heuristic:VainF Torch Pruning Channel Rounding Alignment
- Heuristic:Protectai Llm guard Token Limit Early Guard
- Heuristic:NVIDIA TransformerEngine FP8 Recipe Auto Selection
Environments
- Environment:Sgl project Sglang CUDA GPU Runtime
- Environment:Axolotl ai cloud Axolotl Multi GPU
- Environment:Explodinggradients Ragas Google Drive Backend Environment
- Environment:Lakeraai Pint benchmark Python 310 With Pandas
- Environment:Spcl Graph of thoughts Local LLaMA GPU Inference
- Environment:MarketSquare Robotframework browser Node Runtime
- Environment:Triton inference server Server Docker Container Build
- Environment:Bitsandbytes foundation Bitsandbytes CUDA GPU Runtime
- Environment:Shiyu coder Kronos PyTorch CUDA Environment
- Environment:Huggingface Trl Quantization Environment