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:Huggingface Peft LoRA Causal LM Finetuning
- Workflow:Kubeflow Kubeflow Contributing To Kubeflow
- Workflow:Tencent Ncnn PyTorch Model Conversion and Inference
- Workflow:Openai Evals Building a custom eval
- Workflow:Pytorch Serve Large Model Inference
- Workflow:Facebookresearch Habitat lab Agent Benchmarking
- Workflow:Cohere ai Cohere python AWS Bedrock Deployment
- Workflow:TA Lib Ta lib python Candlestick Pattern Recognition
- Workflow:Promptfoo Promptfoo Project Initialization
- Workflow:ThreeSR Awesome Inference Time Scaling Automated Paper Addition
Principles
- Principle:Confident ai Deepeval Tool Use Evaluation
- Principle:Ggml org Llama cpp Chat Template Application
- Principle:Helicone Helicone Cache Abstraction
- Principle:MaterializeInc Materialize Pipeline Bootstrap
- Principle:FMInference FlexLLMGen HELM Dependency Installation
- Principle:Helicone Helicone Cost Rate Lookup
- Principle:Huggingface Alignment handbook Model Saving and Publishing
- Principle:Protectai Llm guard Sensitive Data Detection
- Principle:MarketSquare Robotframework browser Installation Path Selection
- Principle:Google deepmind Mujoco GLFW Window Management
Implementations
- Implementation:Openai Evals ModelGradedSpec
- Implementation:Puppeteer Puppeteer Bidi HTTPRequest
- Implementation:Langfuse Langfuse Batch Export Stream Transformations
- Implementation:Openai Openai python Fine Tuning Jobs Create
- Implementation:Scikit learn Scikit learn TestingUtils
- Implementation:FlowiseAI Flowise Sidebar
- Implementation:FlagOpen FlagEmbedding MLVU PlotQA Data
- Implementation:CARLA simulator Carla RPC Actor
- Implementation:Mlc ai Mlc llm MLCEngine Generate
- Implementation:Ggml org Llama cpp Graph Header
Heuristics
- Heuristic:Ggml org Llama cpp Context Size Alignment
- Heuristic:Apache Paimon Compression Tuning
- Heuristic:Openai CLIP Linear Probe Regularization C
- Heuristic:Microsoft BIPIA Delta Weight CPU Loading
- Heuristic:FMInference FlexLLMGen OOM Memory Management
- Heuristic:Dotnet Machinelearning Numerical Stability Guards
- Heuristic:Huggingface Peft DoRA Inference Caching
- Heuristic:Deepset ai Haystack Embedding Batch Size And Prefix
- Heuristic:Sktime Pytorch forecasting Encoder Decoder Length Limits
- Heuristic:NVIDIA DALI Memory Pool Tuning
Environments
- Environment:Apache Airflow Python Runtime Environment
- Environment:Vllm project Vllm AArch64 CPU
- Environment:Neuml Txtai GPU Accelerator Environment
- Environment:Sgl project Sglang Triton
- Environment:ClickHouse ClickHouse CI Docker Environment
- Environment:EvolvingLMMs Lab Lmms eval Python Runtime Environment
- Environment:Alibaba MNN GPU OpenCL Environment
- Environment:Microsoft DeepSpeedExamples RLHF Training Environment
- Environment:Microsoft BIPIA Python CUDA GPU Environment
- Environment:Open compass VLMEvalKit Data Storage Environment