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:CarperAI Trlx PPO Sentiment Training
- Workflow:Turboderp org Exllamav2 Text Generation
- Workflow:Dagster io Dagster RAG Pipeline
- Workflow:ARISE Initiative Robomimic Hyperparameter Sweep
- Workflow:Huggingface Open r1 Dataset Pass Rate Filtering
- Workflow:Protectai Llm guard Scanner Benchmarking
- Workflow:Predibase Lorax OpenAI Chat Completion
- Workflow:Heibaiying BigData Notes Hive Data Warehouse Operations
- Workflow:Rapidsai Cuml Multi GPU Distributed ML
- Workflow:ARISE Initiative Robomimic Training Policy From Demonstrations
Principles
- Principle:Princeton nlp SimPO Response Post Processing
- Principle:Microsoft DeepSpeedExamples Model Evaluation And Export
- Principle:Open compass VLMEvalKit Image Inference Orchestration
- Principle:Pytorch Serve vLLM Inference
- Principle:Treeverse LakeFS Import Progress Monitoring
- Principle:Deepspeedai DeepSpeed Inference Execution
- Principle:Infiniflow Ragflow LLM Configuration
- Principle:FlowiseAI Flowise Lead Capture
- Principle:Ggml org Llama cpp HashingUtilities
- Principle:Mlflow Mlflow Predict Function Definition
Implementations
- Implementation:Hiyouga LLaMA Factory RM Workflow
- Implementation:Online ml River Dummy Estimators
- Implementation:Elevenlabs Elevenlabs python RecordingResponse
- Implementation:DistrictDataLabs Yellowbrick ClassificationReport Visualizer
- Implementation:Liu00222 Open Prompt Injection binary search injection
- Implementation:Google deepmind Mujoco Engine Collision Primitive
- Implementation:Ollama Ollama Llama Unicode Data
- Implementation:Microsoft Playwright Pixelmatch
- Implementation:Pola rs Polars LazyFrame Expression Chaining
- Implementation:ClickHouse ClickHouse Find Symbols
Heuristics
- Heuristic:Spotify Luigi Parameter Propagation Decorators
- Heuristic:Helicone Helicone Cost Precision Multiplier
- Heuristic:ThreeSR Awesome Inference Time Scaling Duplicate Detection By Title
- Heuristic:Kserve Kserve VLLM GPU Memory Utilization
- Heuristic:Kserve Kserve Autoscaler Concurrency Target
- Heuristic:Getgauge Taiko Implicit Wait Tuning
- Heuristic:Duckdb Duckdb Test Development Guidelines
- Heuristic:Eric mitchell Direct preference optimization Disable Sampling During Eval
- Heuristic:NVIDIA NeMo Aligner Higher Stability Log Probs
- Heuristic:Explodinggradients Ragas Concurrency And Rate Limiting
Environments
- Environment:Langchain ai Langchain Anthropic API Credentials
- Environment:Hiyouga LLaMA Factory FP8 Training Environment
- Environment:Pola rs Polars Python Runtime Environment
- Environment:Apache Paimon Python Core Runtime
- Environment:Diagram of thought Diagram of thought LLM API
- Environment:Facebookresearch Habitat lab CUDA GPU Training Environment
- Environment:Mistralai Client python Agents Environment
- Environment:OpenHands OpenHands Third Party Runtime Credentials
- Environment:Sail sg LongSpec Training Environment
- Environment:Lakeraai Pint benchmark Python 310 With Transformers