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:Risingwavelabs Risingwave Docker Deployment
- Workflow:Open compass VLMEvalKit API Model Evaluation
- Workflow:Openai CLIP Linear probe evaluation
- Workflow:Mit han lab Llm awq AWQ Model Quantization
- Workflow:Deepspeedai DeepSpeed Pipeline Parallel Training
- Workflow:Infiniflow Ragflow Search Application Setup
- Workflow:Openai Evals Running an eval set
- Workflow:Vespa engine Vespa Linguistics text processing pipeline
- Workflow:Explodinggradients Ragas Prompt Evaluation And Iteration
- Workflow:PeterL1n BackgroundMattingV2 Realtime webcam matting
Principles
- Principle:Webdriverio Webdriverio TestFrameworkIntegration
- Principle:Openai CLIP Image Preprocessing
- Principle:Cleanlab Cleanlab Span Classification Issue Detection
- Principle:Ggml org Ggml Vision Encoder Execution
- Principle:Ollama Ollama Base Model Resolution
- Principle:Confident ai Deepeval Component Instrumentation
- Principle:Openai Openai python Image Result Processing
- Principle:Microsoft Autogen Graph Execution
- Principle:Shiyu coder Kronos Tokenizer Loading
- Principle:Nightwatchjs Nightwatch Module Import
Implementations
- Implementation:Ollama Ollama XCreate Quantize
- Implementation:Arize ai Phoenix RAG Span Helpers
- Implementation:Langchain ai Langchain BaseChatModel Generate With Cache
- Implementation:ClickHouse ClickHouse Phdr Cache
- Implementation:Huggingface Transformers AutoModelForCausalLM From Pretrained For Quantization
- Implementation:Zai org CogVideo DDIM Export Latents To Video
- Implementation:MaterializeInc Materialize Helm Operator Values
- Implementation:Google deepmind Dm control Composer Task
- Implementation:Evidentlyai Evidently Compare
- Implementation:Haosulab ManiSkill MJCFLoaderInternal
Heuristics
- Heuristic:Haotian liu LLaVA Quantization MM Projector Exclusion
- Heuristic:Snorkel team Snorkel Minimum Three LFs
- Heuristic:Kornia Kornia Lazy Loading Optional Deps
- Heuristic:Facebookresearch Habitat lab Mini Batch Environment Divisibility
- Heuristic:MarketSquare Robotframework browser Docker Chrome Security
- Heuristic:Facebookresearch Audiocraft Audio Normalization Strategies
- Heuristic:Kubeflow Kubeflow Kustomize Build Pipe Apply Pattern
- Heuristic:Langfuse Langfuse LLM Rate Limit 24h Abandon
- Heuristic:Lm sys FastChat Tokenizer Offset Correction
- Heuristic:Kserve Kserve Autoscaler Concurrency Target
Environments
- Environment:Microsoft Playwright Platform Support Environment
- Environment:Google deepmind Mujoco MJX Warp CUDA Environment
- Environment:Mlc ai Web llm WebGPU Browser Runtime
- Environment:Sktime Pytorch forecasting Core Python Dependencies
- Environment:TA Lib Ta lib python Python Build Environment
- Environment:Mlfoundations Open flamingo PyTorch CUDA Distributed
- Environment:Bentoml BentoML NVIDIA GPU Resource
- Environment:Unstructured IO Unstructured Profiling Tools
- Environment:Google deepmind Mujoco Python Bindings Environment
- Environment:ARISE Initiative Robomimic PyTorch CUDA Environment