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:Langgenius Dify RAG Pipeline Development
- Workflow:Tensorflow Tfjs GPT2 Text Generation
- Workflow:ThreeSR Awesome Inference Time Scaling Automated Paper Addition
- Workflow:PacktPublishing LLM Engineers Handbook Model Evaluation
- Workflow:Neuml Txtai Agent Orchestration
- Workflow:Intel Ipex llm QLoRA Finetuning
- Workflow:Groq Groq python Chat Completion
- Workflow:MarketSquare Robotframework browser Plugin Development
- Workflow:Openai Openai agents python Streaming Agent Execution
- Workflow:Turboderp org Exllamav2 Bulk Dataset Inference
Principles
- Principle:Triton inference server Server Observability Testing
- Principle:PrefectHQ Prefect Flow Orchestration
- Principle:Facebookresearch Habitat lab Data Recording
- Principle:Nightwatchjs Nightwatch Writing Test Cases
- Principle:Ggml org Llama cpp Performance Benchmarking
- Principle:Speechbrain Speechbrain Dataset Specific Data Preparation
- Principle:Cypress io Cypress Component Mounting
- Principle:Online ml River Multi Step Forecasting
- Principle:Huggingface Optimum Meta Device Initialization
- Principle:Cleanlab Cleanlab Segmentation Issue Visualization
Implementations
- Implementation:Haosulab ManiSkill GymUtils
- Implementation:Microsoft Onnxruntime CUDA GatherNDGrad
- Implementation:Speechbrain Speechbrain Eval ESC50 Interpret
- Implementation:Microsoft Semantic kernel ImportPluginFromOpenApiAsync
- Implementation:Ucbepic Docetl Dataset Medical Transcripts
- Implementation:Datahub project Datahub Run Quickstart Preflight Checks
- Implementation:FlowiseAI Flowise OverrideConfig
- Implementation:Facebookresearch Audiocraft Audio write
- Implementation:Zai org CogVideo LLM Flux Gradio
- Implementation:Hiyouga LLaMA Factory V1 Arg Utils
Heuristics
- Heuristic:Bitsandbytes foundation Bitsandbytes Compute Dtype Mismatch Warning
- Heuristic:OpenHands OpenHands Streamable HTTP Over SSE
- Heuristic:Langfuse Langfuse Fail Open Resilience Pattern
- Heuristic:Lm sys FastChat Vicuna SFT Training Hyperparameters
- Heuristic:Pola rs Polars Avoid Lambda In Aggregation
- Heuristic:OWASP Www project top 10 for large language model applications Deliberately Insecure Code Isolation
- Heuristic:Huggingface Optimum GPTQ Quantization Defaults
- Heuristic:Pytorch Serve Ampere Tensor Core Optimization
- Heuristic:Dotnet Machinelearning Sparsity Threshold Optimization
- Heuristic:LLMBook zh LLMBook zh github io IGNORE INDEX Loss Masking
Environments
- Environment:Sgl project Sglang Distributed
- Environment:CarperAI Trlx DeepSpeed Multi GPU
- Environment:Mit han lab Llm awq CUDA Build Environment
- Environment:Alibaba MNN HuggingFace Ecosystem Environment
- Environment:NVIDIA DALI CMake Build Environment
- Environment:Huggingface Optimum Python Core Dependencies
- Environment:BerriAI Litellm Python Runtime
- Environment:Iamhankai Forest of Thought OpenAI API Credentials
- Environment:Microsoft Playwright Browser Binaries Environment
- Environment:Lance format Lance Cloud Storage Credentials