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:Pytorch Serve LLM Deployment vLLM
- Workflow:Deepspeedai DeepSpeed AutoTP Training
- Workflow:Romsto Speculative Decoding Speculative Decoding Inference
- Workflow:Microsoft Agent framework Multi Agent Concurrent Orchestration
- Workflow:Mistralai Client python GCP Chat Completion
- Workflow:Microsoft Agent framework Basic Agent Creation
- Workflow:Huggingface Transformers Model Quantization
- Workflow:Datahub project Datahub Metadata Ingestion Pipeline
- Workflow:CarperAI Trlx RLHF Summarization Pipeline
- Workflow:AUTOMATIC1111 Stable diffusion webui Checkpoint merging
Principles
- Principle:Princeton nlp Tree of thought llm LLM API Wrapping
- Principle:Ggml org Llama cpp GGUF File Operations
- Principle:Google deepmind Mujoco Binary Model Loading
- Principle:Predibase Lorax Inference Result Evaluation
- Principle:Ggml org Llama cpp Multimodal
- Principle:Junyanz Pytorch CycleGAN and pix2pix Image Saving
- Principle:Langchain ai Langgraph Async Checkpoint Persistence
- Principle:AUTOMATIC1111 Stable diffusion webui Image preprocessing and latent encoding
- Principle:DistrictDataLabs Yellowbrick Joint Plot Analysis
- Principle:Snorkel team Snorkel Transformation Application
Implementations
- Implementation:NVIDIA TransformerEngine Ops Fused Forward Linear Bias Add
- Implementation:FlagOpen FlagEmbedding LLARA Finetune Modeling
- Implementation:CrewAIInc CrewAI MongoDB Vector Utils
- Implementation:SeleniumHQ Selenium Closure Aria Attributes
- Implementation:NVIDIA NeMo Curator SemanticDeduplicationWorkflow for Video
- Implementation:HKUDS AI Trader Ainvoke With Retry
- Implementation:Evidentlyai Evidently Custom Descriptors
- Implementation:Interpretml Interpret To Jsonable
- Implementation:Unstructured IO Unstructured Golden File Fixtures Local
- Implementation:Evidentlyai Evidently Legacy Load Snapshots
Heuristics
- Heuristic:Microsoft Onnxruntime Convergence Debugging Tips
- Heuristic:Microsoft Agent framework Declaration Only Tools Pattern
- Heuristic:Elevenlabs Elevenlabs python TTS Model Selection
- Heuristic:Treeverse LakeFS Batch Delay Tuning
- Heuristic:NVIDIA NeMo Aligner Adam State Offloading Tip
- Heuristic:Helicone Helicone Anthropic Cache Double Count Prevention
- Heuristic:Datahub project Datahub Venv Copies Mode
- Heuristic:Langgenius Dify SQL Escape Backslash First
- Heuristic:Openai Evals Chat Format Recommendation
- Heuristic:Infiniflow Ragflow Agent Max Rounds Strategy
Environments
- Environment:Triton inference server Server Docker Container Build
- Environment:Openai Whisper PyTorch CUDA
- Environment:Ucbepic Docetl Docker Deployment
- Environment:Zai org CogVideo Diffusers Finetuning Environment
- Environment:Bentoml BentoML NVIDIA GPU Resource
- Environment:Langfuse Langfuse Redis 7 Queue Cache
- Environment:NVIDIA NeMo Aligner TensorRT LLM Acceleration Environment
- Environment:Vllm project Vllm NVIDIA CUDA
- Environment:OpenHands OpenHands SaaS Server Environment
- Environment:Microsoft LoRA NLU Conda Environment