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:Langgenius Dify Knowledge Base Creation
- Workflow:Treeverse LakeFS External Data Import
- Workflow:Truera Trulens RAG Evaluation With LangChain
- Workflow:Infiniflow Ragflow Search Application Setup
- Workflow:Intel Ipex llm Pipeline Parallel Inference
- Workflow:Microsoft BIPIA Black Box Defense Evaluation
- Workflow:OpenRLHF OpenRLHF Rejection Sampling
- Workflow:Tencent Ncnn Image Classification Inference
- Workflow:Microsoft Onnxruntime On Device Training
- Workflow:OpenBMB UltraFeedback GPT4 Preference Annotation
Principles
- Principle:Openai Openai node Tool Loop Resolution
- Principle:ClickHouse ClickHouse DNS Resolution
- Principle:Getgauge Taiko Runtime Configuration
- Principle:Sktime Pytorch forecasting NHiTS Architecture
- Principle:Isaac sim IsaacGymEnvs Automatic Domain Randomization
- Principle:AUTOMATIC1111 Stable diffusion webui Extension Management
- Principle:Langchain ai Langgraph Store Batch Operations
- Principle:LLMBook zh LLMBook zh github io Symmetric Quantization
- Principle:Langfuse Langfuse Trace Sampling
- Principle:Bentoml BentoML Service Dependency Injection
Implementations
- Implementation:Mlflow Mlflow Openai Autolog
- Implementation:FlagOpen FlagEmbedding FlagAutoModel From Finetuned
- Implementation:Truera Trulens Record Viewer Utils
- Implementation:Triton inference server Server MemoryAllocTest
- Implementation:Deepspeedai DeepSpeed HybridEngine Generate
- Implementation:Farama Foundation Gymnasium Make Vec
- Implementation:OpenHands OpenHands DeviceCode
- Implementation:CarperAI Trlx Default PPO Config
- Implementation:OpenHands OpenHands Button
- Implementation:FlagOpen FlagEmbedding LLM Embedder Eval PopQA
Heuristics
- Heuristic:Langchain ai Langgraph Durability Mode Selection
- Heuristic:Vllm project Vllm Batch Size Hardware Scaling
- Heuristic:Alibaba MNN NC4HW4 Data Layout
- Heuristic:Alibaba ROLL KL Coefficient Tuning
- Heuristic:Mlc ai Mlc llm Metal KV Cache Capacity Limit
- Heuristic:Cohere ai Cohere python HTTP Retry Backoff Strategy
- Heuristic:Gretelai Gretel synthetics Mixed Precision Training Tradeoff
- Heuristic:Open compass VLMEvalKit API Retry With Random Delay
- Heuristic:Kornia Kornia Morphology Engine Selection
- Heuristic:Microsoft Semantic kernel Experimental Feature Opt In
Environments
- Environment:Sgl project Sglang OpenAI
- Environment:Langchain ai Langchain OpenAI API Credentials
- Environment:Apache Hudi Docker Demo Environment
- Environment:Googleapis Python genai Vertex AI Service Account
- Environment:Sgl project Sglang Python Dependencies
- Environment:ARISE Initiative Robomimic HDF5 Data Dependencies
- Environment:Kserve Kserve Leader Worker Set
- Environment:TobikoData Sqlmesh Dbt Compatibility
- Environment:Apache Spark Release Build Environment
- Environment:Haosulab ManiSkill GPU CUDA Simulation