Main Page
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:Google research Deduplicate text datasets Wiki40B TFDS deduplication
- Workflow:Fede1024 Rust rdkafka Async Stream Processing
- Workflow:Open compass VLMEvalKit API Model Evaluation
- Workflow:Google deepmind Dm control Manipulation Task Setup
- Workflow:Explodinggradients Ragas Prompt Evaluation And Iteration
- Workflow:LaurentMazare Tch rs Pretrained Image Classification
- Workflow:Openai Openai node Fine Tuning
- Workflow:Microsoft Semantic kernel Plugin Integration And Function Calling
- Workflow:Haotian liu LLaVA LoRA Finetuning
- Workflow:Zai org CogVideo Diffusers LoRA Finetuning
Principles
- Principle:Duckdb Duckdb Random Number Generation
- Principle:Pytorch Serve Inference Pipeline
- Principle:Haotian liu LLaVA Checkpoint Extraction
- Principle:OpenHands OpenHands Server Startup
- Principle:Facebookresearch Audiocraft Generation Parameter Configuration
- Principle:Ray project Ray Cross Language Serialization
- Principle:Huggingface Datasets Dataset Object Construction
- Principle:Langgenius Dify Plugin Discovery
- Principle:Ggml org Llama cpp Diffusion Text Generation
- Principle:Mlflow Mlflow Model Loading
Implementations
- Implementation:BerriAI Litellm Core Helpers
- Implementation:Apache Paimon Schema With Lance Format
- Implementation:Infiniflow Ragflow LLM Constants
- Implementation:Sgl project Sglang CPU QKV Projection
- Implementation:Microsoft Onnxruntime InferenceSession Get Inputs
- Implementation:Eric mitchell Direct preference optimization Concatenated Forward
- Implementation:Cleanlab Cleanlab OD Visualize
- Implementation:ARISE Initiative Robomimic TrainUtils load data for training
- Implementation:Pyro ppl Pyro SeedMessenger
- Implementation:Huggingface Diffusers Setup Package Configuration
Heuristics
- Heuristic:Interpretml Interpret Categorical Float Conversion Gotcha
- Heuristic:Huggingface Alignment handbook QLoRA Learning Rate Scaling
- Heuristic:DataTalksClub Data engineering zoomcamp Kafka Consumer Poll Timeout
- Heuristic:Fastai Fastbook Weight Decay Tuning
- Heuristic:Testtimescaling Testtimescaling github io Skip CI Commit Tag
- Heuristic:Princeton nlp SimPO Concatenated Forward Pass
- Heuristic:Alibaba MNN NC4HW4 Data Layout
- Heuristic:Apache Druid Explore Compare Query Strategy
- Heuristic:AnswerDotAI RAGatouille FAISS Vs PyTorch KMeans Indexing
- Heuristic:FlowiseAI Flowise Edge Connection Type Matching
Environments
- Environment:Langchain ai Langchain Python 3 10 Runtime
- Environment:Anthropics Anthropic sdk python GCP Vertex Environment
- Environment:Huggingface Transformers PEFT Adapter Env
- Environment:Tencent Ncnn PyTorch Environment
- Environment:Eric mitchell Direct preference optimization Python Dependencies
- Environment:Axolotl ai cloud Axolotl CUDA GPU
- Environment:Langchain ai Langchain OpenAI API Credentials
- Environment:Allenai Open instruct Beaker Cluster
- Environment:Ggml org Llama cpp CUDA GPU Environment
- Environment:Confident ai Deepeval Python 3 9 Runtime