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:Cleanlab Cleanlab Object Detection Label Quality
- Workflow:Open compass VLMEvalKit Adding Custom Benchmark
- Workflow:Sdv dev SDV Sequential data synthesis
- Workflow:Romsto Speculative Decoding Ngram Assisted Speculative Decoding
- Workflow:Langchain ai Langgraph Human in the Loop Agent
- Workflow:Arize ai Phoenix Prompt Management Pipeline
- Workflow:CarperAI Trlx ILQL Offline Training
- Workflow:Eric mitchell Direct preference optimization SFT Training
- Workflow:Huggingface Datatrove Dataset Tokenization
- Workflow:NVIDIA NeMo Aligner RLHF PPO Training
Principles
- Principle:EvolvingLMMs Lab Lmms eval Parallel Inference
- Principle:Microsoft BIPIA Results Analysis
- Principle:Trailofbits Fickling Static Safety Analysis
- Principle:Unslothai Unsloth Quantized Model Loading
- Principle:Triton inference server Server TRT LLM Model Repository Setup
- Principle:Interpretml Interpret EBM Model Merging
- Principle:OpenHands OpenHands Action Server Startup
- Principle:Dagster io Dagster LLM Fine Tuning Orchestration
- Principle:Spotify Luigi Hadoop Job Configuration
- Principle:Ggml org Llama cpp Eval Callbacks
Implementations
- Implementation:Infiniflow Ragflow CreateAgentForm Component
- Implementation:Hpcaitech ColossalAI LongBenchDataset
- Implementation:Open compass VLMEvalKit VLMR1Chat
- Implementation:NVIDIA NeMo Curator JSONLReader
- Implementation:NVIDIA TransformerEngine TE LayerNorm
- Implementation:FlowiseAI Flowise OnConnect
- Implementation:FlowiseAI Flowise GetNodesByCategory
- Implementation:EvolvingLMMs Lab Lmms eval LongVT Utils
- Implementation:Open compass VLMEvalKit Spatial457
- Implementation:Online ml River FeatureExtraction Vectorize
Heuristics
- Heuristic:Mage ai Mage ai Sorted Data Bookmark Strategy
- Heuristic:Junyanz Pytorch CycleGAN and pix2pix Adam Beta1 Half
- Heuristic:Mlc ai Web llm Grammar Matcher Reuse
- Heuristic:Intel Ipex llm LoRA Target All Linear Layers
- Heuristic:Huggingface Datasets Parquet Shard Sizing
- Heuristic:Puppeteer Puppeteer Headless Linux Requirements
- Heuristic:Lance format Lance Warning Deprecated Legacy Encodings
- Heuristic:Haifengl Smile BFGS Convergence Tuning
- Heuristic:Dotnet Machinelearning FastTree Default Hyperparameters
- Heuristic:Mlc ai Mlc llm BLAS Dispatch Decision
Environments
- Environment:Langgenius Dify Docker Deployment Environment
- Environment:Huggingface Trl vLLM Generation Environment
- Environment:MarketSquare Robotframework browser Docker Container
- Environment:Googleapis Python genai Vertex AI Service Account
- Environment:Infiniflow Ragflow GPU CUDA Environment
- Environment:Pyro ppl Pyro CUDA GPU Acceleration
- Environment:TobikoData Sqlmesh GitHub CICD Runner
- Environment:Risingwavelabs Risingwave Docker Deployment Environment
- Environment:Lm sys FastChat GPU CUDA Inference
- Environment:Fastai Fastbook Jupyter Notebook Environment