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:LMCache LMCache P2P KV Cache Sharing
- Workflow:ClickHouse ClickHouse Server Deployment
- Workflow:Lucidrains X transformers Encoder Decoder Sequence to Sequence
- Workflow:Hpcaitech ColossalAI Supervised Finetuning
- Workflow:Triton inference server Server Quickstart Model Deployment
- Workflow:Neuml Txtai Pipeline Workflow Chaining
- Workflow:Hiyouga LLaMA Factory LoRA SFT Finetuning
- Workflow:ARISE Initiative Robosuite Human Demonstration Collection
- Workflow:Ray project Ray Cross Language Invocation
- Workflow:Apache Shardingsphere Shadow Rule Configuration
Principles
- Principle:Alibaba MNN Neural Network Inference
- Principle:Vllm project Vllm Multimodal Generation
- Principle:Langchain ai Langchain Standard Unit Testing
- Principle:DataTalksClub Data engineering zoomcamp Dbt Marts Layer
- Principle:Intel Ipex llm ReLoRA Training
- Principle:Farama Foundation Gymnasium Environment Error Handling
- Principle:AUTOMATIC1111 Stable diffusion webui Textual inversion training loop
- Principle:Romsto Speculative Decoding Ngram Storage
- Principle:Duckdb Duckdb Binary Signing
- Principle:Ggml org Llama cpp Performance Benchmarking
Implementations
- Implementation:Huggingface Datatrove SentenceStats
- Implementation:Groq Groq python BinaryAPIResponse Usage
- Implementation:Evidentlyai Evidently SDK Models
- Implementation:EvolvingLMMs Lab Lmms eval Lmms Is Simple
- Implementation:Openai Openai agents python Handoff Helper
- Implementation:Vibrantlabsai Ragas InstanceRubrics
- Implementation:Ggml org Ggml Sam build fast graph
- Implementation:Elevenlabs Elevenlabs python WorkspaceResourceType
- Implementation:Microsoft Onnxruntime CheckpointProperty
- Implementation:FlowiseAI Flowise SuggestionList
Heuristics
- Heuristic:Run llama Llama index Chunk Size Optimization
- Heuristic:Zai org CogVideo LoRA Configuration Tips
- Heuristic:Trailofbits Fickling Force Flag Bypass
- Heuristic:Huggingface Datatrove MinHash Parameter Tuning
- Heuristic:PeterL1n BackgroundMattingV2 Checkpoint Interval Tuning
- Heuristic:Openai Evals Thread Tuning
- Heuristic:Mistralai Client python Resource Context Manager
- Heuristic:Roboflow Rf detr Batch Size Memory Tradeoff
- Heuristic:Huggingface Alignment handbook Gradient Checkpointing Use Cache
- Heuristic:Haosulab ManiSkill Initial Pose Performance
Environments
- Environment:Openai Openai node WebSocket Dependency
- Environment:Mistralai Client python Python SDK Environment
- Environment:Kubeflow Pipelines Kubernetes Cluster
- Environment:Iterative Dvc Git SCM Environment
- Environment:Mistralai Client python Azure Deployment Environment
- Environment:Vllm project Vllm Python
- Environment:Togethercomputer Together python Fine Tuning Data Requirements
- Environment:Hiyouga LLaMA Factory Core Python GPU Environment
- Environment:MarketSquare Robotframework browser Node Runtime
- Environment:Risingwavelabs Risingwave Dashboard Node Environment