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:Langchain ai Langchain Adding Partner Integration
- Workflow:Haotian liu LLaVA Benchmark Evaluation
- Workflow:Sgl project Sglang ModelOpt Quantization And Export
- Workflow:VainF Torch Pruning Vision Transformer Pruning
- Workflow:Anthropics Anthropic sdk python Streaming Message Interaction
- Workflow:Vllm project Vllm Vision Language Inference
- Workflow:Iamhankai Forest of Thought FoT Benchmark Evaluation
- Workflow:TA Lib Ta lib python Streaming Indicator Computation
- Workflow:DataExpert io Data engineer handbook Dimensional Data Modeling Environment Setup
- Workflow:NVIDIA NeMo Aligner Reward Model Training
Principles
- Principle:Pytorch Serve vLLM Inference
- Principle:CrewAIInc CrewAI Training Execution
- Principle:Alibaba MNN Model Format Conversion
- Principle:Ray project Ray Object Store Retrieval
- Principle:FMInference FlexLLMGen CUDA Type Conversion
- Principle:Neuml Txtai Sparse Retrieval
- Principle:Lucidrains X transformers Variational Latent Language Modeling
- Principle:Spotify Luigi Web Visualiser Monitoring
- Principle:Huggingface Datatrove LLM Inference Execution
- Principle:AUTOMATIC1111 Stable diffusion webui SD3 Diffusion Pipeline
Implementations
- Implementation:Hiyouga LLaMA Factory Attention Config
- Implementation:Lance format Lance Java DeleteOp
- Implementation:Microsoft DeepSpeedExamples NvidiaBert DatasetProvider
- Implementation:Allenai Open instruct TokenizerConfig
- Implementation:Turboderp org Exllamav2 Model Diff
- Implementation:Microsoft Playwright PipeTransport
- Implementation:CrewAIInc CrewAI CrewAI Tools Library
- Implementation:AUTOMATIC1111 Stable diffusion webui Webui Disk Cache
- Implementation:Microsoft Onnxruntime OrtTensorRTProviderOptions
- Implementation:Apache Druid Kubernetes Operator Main
Heuristics
- Heuristic:Google deepmind Dm control Warning Deprecated Legacy Base Walker
- Heuristic:Norrrrrrr lyn WAInjectBench L2 Normalize CLIP Embeddings
- Heuristic:Langchain ai Langchain Error Context Preservation
- Heuristic:Openai Evals Model Graded Eval Design
- Heuristic:Openai Whisper Log Probability Threshold
- Heuristic:Farama Foundation Gymnasium Sync Vs Async VectorEnv Selection
- Heuristic:SeldonIO Seldon core Model Scheduling Preference Tip
- Heuristic:Spcl Graph of thoughts Backoff Retry On API Errors
- Heuristic:Allenai Open instruct NCCL CUMEM Disable
- Heuristic:Confident ai Deepeval Dotenv Loading Order
Environments
- Environment:Unstructured IO Unstructured Profiling Tools
- Environment:Apache Airflow Development Contributor Environment
- Environment:Huggingface Alignment handbook Evaluation Tools
- Environment:Openclaw Openclaw Docker Deployment Environment
- Environment:Bentoml BentoML BentoCloud Credentials
- Environment:Openclaw Openclaw State Directory And Credentials
- Environment:Huggingface Optimum Tensor Parallelization Environment
- Environment:Vllm project Vllm AArch64 CPU
- Environment:Recommenders team Recommenders Python Core Dependencies
- Environment:Vllm project Vllm Environment Variables