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:Intel Ipex llm RAG With LangChain
- Workflow:OpenHands OpenHands Organization Onboarding
- Workflow:TA Lib Ta lib python Abstract API Usage
- Workflow:Haosulab ManiSkill Custom Task Development
- Workflow:Google deepmind Mujoco GPU batched simulation MJX
- Workflow:FMInference FlexLLMGen Text Completion API
- Workflow:Fastai Fastbook Neural Network From Scratch
- Workflow:Predibase Lorax Multi Adapter Merging
- Workflow:Apache Shardingsphere Dynamic Rule Configuration Change
- Workflow:Protectai Modelscan CLI Model Scanning
Principles
- Principle:TobikoData Sqlmesh Production Promotion
- Principle:Tensorflow Serving Hardware Tuning
- Principle:Microsoft DeepSpeedExamples ZeRO Inference Environment
- Principle:Farama Foundation Gymnasium Episode Time Limiting
- Principle:ClickHouse ClickHouse SIMD Memory Comparison
- Principle:Huggingface Diffusers Post Processing
- Principle:Elevenlabs Elevenlabs python Batch Speech to Text
- Principle:Vespa engine Vespa Subscriber Shutdown
- Principle:Alibaba MNN LLM Runtime Configuration
- Principle:Spotify Luigi Static Type Checking
Implementations
- Implementation:OpenHands OpenHands DeviceCode
- Implementation:Sgl project Sglang Scalar Type
- Implementation:Predibase Lorax BGMV Shrink Kernel
- Implementation:NVIDIA NeMo Curator CosmosEmbed1Model
- Implementation:CrewAIInc CrewAI Embedder Config
- Implementation:Ggml org Llama cpp IMatrixCollector
- Implementation:DistrictDataLabs Yellowbrick RadViz Visualizer
- Implementation:Ollama Ollama Llama Model GLM4
- Implementation:Ollama Ollama XTools WebSearch
- Implementation:Helicone Helicone XAI Model Definitions
Heuristics
- Heuristic:Zai org CogVideo Frame Count and Resolution Constraints
- Heuristic:Farama Foundation Gymnasium Seeding Determinism Best Practices
- Heuristic:Romsto Speculative Decoding KV Cache Instability
- Heuristic:ARISE Initiative Robosuite Hard Reset Vs Soft Reset
- Heuristic:ContextualAI HALOs Humanline Clamping
- Heuristic:Protectai Modelscan Unknown Opcodes Assume Critical
- Heuristic:Treeverse LakeFS Warning Deprecated InternalApi Methods
- Heuristic:Run llama Llama index Finetuning Warmup Steps
- Heuristic:Mlc ai Web llm Low Resource Model Selection
- Heuristic:Fastai Fastbook Learning Rate Finder Rule
Environments
- Environment:Langgenius Dify Docker Deployment Environment
- Environment:Bentoml BentoML NVIDIA GPU Resource
- Environment:Huggingface Datasets PyTorch Integration
- Environment:Microsoft Onnxruntime CUDA GPU Environment
- Environment:Datajuicer Data juicer LLM API Credentials Environment
- Environment:Apache Druid Web Console Development
- Environment:Apache Airflow Python Runtime Environment
- Environment:OpenBMB UltraFeedback Python GPU Environment
- Environment:Kserve Kserve Gateway API
- Environment:Spcl Graph of thoughts Local LLaMA GPU Inference