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:Volcengine Verl Multi Turn Tool Use Training
- Workflow:BerriAI Litellm SDK Completion
- Workflow:Huggingface Open r1 Dataset Pass Rate Filtering
- Workflow:Bentoml BentoML BentoCloud Deployment
- Workflow:LMCache LMCache Disaggregated Prefill
- Workflow:HKUDS AI Trader Agent Decision Loop
- Workflow:Cohere ai Cohere python Chat Completion
- Workflow:Mit han lab Llm awq AWQ Model Quantization
- Workflow:Webdriverio Webdriverio Standalone Browser Automation
- Workflow:Huggingface Peft Prompt Tuning Classification
Principles
- Principle:InternLM Lmdeploy W8A8 Quantized Inference
- Principle:Triton inference server Server Jetson Edge Deployment
- Principle:Deepset ai Haystack Cross Encoder Reranking
- Principle:Huggingface Datatrove WARC Archive Reading
- Principle:Princeton nlp SimPO Configuration Parsing
- Principle:Huggingface Datatrove Word Level Statistics
- Principle:PacktPublishing LLM Engineers Handbook Model Merging And Publishing
- Principle:DistrictDataLabs Yellowbrick RadViz Visualization
- Principle:Bigscience workshop Petals Server Configuration
- Principle:Huggingface Datatrove Tokenized Dataset Loading
Implementations
- Implementation:Eventual Inc Daft DataFrame Write Parquet
- Implementation:Langgenius Dify UseModels
- Implementation:CrewAIInc CrewAI Arxiv Paper Tool
- Implementation:BerriAI Litellm Vector Store Files API
- Implementation:DistrictDataLabs Yellowbrick Manifold Visualizer
- Implementation:NVIDIA NeMo Curator ImageWriterStage
- Implementation:Mistralai Client python Embeddings Create
- Implementation:Kserve Kserve GPU Cluster Credentials
- Implementation:Interpretml Interpret DecisionListClassifier
- Implementation:Ray project Ray Serve Shutdown
Heuristics
- Heuristic:AnswerDotAI RAGatouille Auto Batch Size For Long Documents
- Heuristic:Trailofbits Fickling Injection Mode Selection
- Heuristic:Ggml org Ggml Memory Allocation Strategy
- Heuristic:Hpcaitech ColossalAI Empty Cache Between Phases
- Heuristic:Iamhankai Forest of Thought Tree Iteration Scaling
- Heuristic:Deepspeedai DeepSpeed FP16 Convergence Tips
- Heuristic:OWASP Www project top 10 for large language model applications SHA Pinning For GitHub Actions
- Heuristic:Togethercomputer Together python Retry Backoff Strategy
- Heuristic:Wandb Weave Concurrency Deadlock Prevention
- Heuristic:ChenghaoMou Text dedup Fingerprint Batch Size One
Environments
- Environment:Marker Inc Korea AutoRAG Korean NLP Dependencies
- Environment:Getgauge Taiko Node Runtime
- Environment:Explodinggradients Ragas Google Drive Backend Environment
- Environment:Lakeraai Pint benchmark Python 310 With Transformers
- Environment:Ray project Ray Python Runtime Environment
- Environment:Webdriverio Webdriverio Cloud Service Credentials
- Environment:Testtimescaling Testtimescaling github io GitHub Actions Runner
- Environment:Cypress io Cypress Linux Display Server
- Environment:InternLM Lmdeploy CUDA GPU Runtime
- Environment:Huggingface Alignment handbook BitsAndBytes CUDA