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:Hiyouga LLaMA Factory Model Inference and Serving
- Workflow:Triton inference server Server Quickstart Model Deployment
- Workflow:Deepseek ai Janus Rectified Flow Image Generation
- Workflow:Dotnet Machinelearning Binary Classification Pipeline
- Workflow:Guardrails ai Guardrails Server Deployment
- Workflow:Fede1024 Rust rdkafka At Least Once Processing
- Workflow:EvolvingLMMs Lab Lmms eval Distributed Multi GPU Evaluation
- Workflow:Neuml Txtai Semantic Search Pipeline
- Workflow:Sgl project Sglang Structured Output Generation
- Workflow:Turboderp org Exllamav2 Interactive Chat
Principles
- Principle:Openai Openai agents python Streamed Result Access
- Principle:Openclaw Openclaw Skill Loading
- Principle:Tensorflow Tfjs Convolutional Neural Networks
- Principle:Run llama Llama index Finetuning Job Launch
- Principle:Google deepmind Mujoco Model Validation
- Principle:Promptfoo Promptfoo Telemetry Collection
- Principle:Promptfoo Promptfoo Strategy Application
- Principle:Huggingface Diffusers Checkpoint Format Identification
- Principle:Langchain ai Langchain Tool Definition
- Principle:Bentoml BentoML Deployment Lifecycle Management
Implementations
- Implementation:Open compass VLMEvalKit MEGABench Metric Type
- Implementation:Huggingface Transformers Modular Model Detector
- Implementation:LMCache LMCache Observability
- Implementation:Webdriverio Webdriverio WDIOReporter Base Class
- Implementation:Lm sys FastChat Deduplication
- Implementation:Ollama Ollama Llama Sampling Engine
- Implementation:FlagOpen FlagEmbedding LLM Reranker Evaluate
- Implementation:Microsoft Playwright BidiInput
- Implementation:Kornia Kornia ONNXSequential Call
- Implementation:LMCache LMCache KVController Lookup
Heuristics
- Heuristic:Haosulab ManiSkill Num Envs Backend Selection
- Heuristic:Infiniflow Ragflow Hybrid Search Fallback Strategy
- Heuristic:Microsoft Autogen Agent Thread Safety
- Heuristic:Openai CLIP FP16 FP32 Dtype Handling
- Heuristic:Apache Dolphinscheduler Gzip Compression Threshold
- Heuristic:Facebookresearch Audiocraft Gradient Balancing For Multi Loss
- Heuristic:OpenRLHF OpenRLHF vLLM Embedding Resize Warning
- Heuristic:Apache Paimon Vector Index Configuration Tips
- Heuristic:Allenai Open instruct GPU Memory Utilization
- Heuristic:Dotnet Machinelearning LDA Thread Reservation
Environments
- Environment:LLMBook zh LLMBook zh github io Bitsandbytes Quantization Environment
- Environment:Kubeflow Kubeflow Git GitHub Environment
- Environment:Langgenius Dify Redis And Celery Environment
- Environment:Neuml Txtai Docker Deployment Environment
- Environment:Tencent Ncnn Vulkan Environment
- Environment:Tensorflow Serving GPU CUDA Environment
- Environment:Fede1024 Rust rdkafka CI Test Runner
- Environment:Microsoft Autogen Studio Server Environment
- Environment:Bigscience workshop Petals Python Hivemind
- Environment:Risingwavelabs Risingwave Java Connector Environment