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:Microsoft Agent framework Basic Agent Creation
- Workflow:LMCache LMCache CacheBlend KV Reuse
- Workflow:Heibaiying BigData Notes HBase Java CRUD Operations
- Workflow:Huggingface Trl Supervised Finetuning
- Workflow:Nightwatchjs Nightwatch Custom Commands And Assertions
- Workflow:Haotian liu LLaVA Single Image Inference
- Workflow:Sdv dev SDV Constrained synthesis
- Workflow:Spotify Luigi Database Ingestion Pipeline
- Workflow:Mlflow Mlflow Model Serving
- Workflow:Cleanlab Cleanlab Token Classification Label Quality
Principles
- Principle:FMInference FlexLLMGen BFloat16 Mixed Precision Optimization
- Principle:Haosulab ManiSkill Sim2Real Policy Training
- Principle:Roboflow Rf detr Training Loop Execution
- Principle:Allenai Open instruct DPO Loss Dispatch
- Principle:Ggml org Ggml WebGPU Computation
- Principle:Infiniflow Ragflow Chunk Filtering
- Principle:Bitsandbytes foundation Bitsandbytes CPU SIMD Dequantization
- Principle:Langchain ai Langchain Document Preparation
- Principle:OpenHands OpenHands Base App Initialization
- Principle:Truera Trulens LangGraph Agent Construction
Implementations
- Implementation:Datahub project Datahub Pipeline Create And Run
- Implementation:EvolvingLMMs Lab Lmms eval Regression Testing
- Implementation:Wandb Weave Prerelease Dry Run
- Implementation:Google deepmind Dm control Composer Arena
- Implementation:FlowiseAI Flowise StarterPrompts
- Implementation:Apache Paimon DataTypes Python
- Implementation:Predibase Lorax AWQ WQLinear
- Implementation:Alibaba ROLL DPO Cluster Setup
- Implementation:Apache Paimon KeyValueDataWriter
- Implementation:Open compass VLMEvalKit MME Reasoning
Heuristics
- Heuristic:Shiyu coder Kronos Learning Rate And Optimizer Tuning
- Heuristic:Pyro ppl Pyro MCMC Warmup Adaptation
- Heuristic:Deepset ai Haystack Warning Deprecated TransformersSimilarityRanker
- Heuristic:Online ml River Hoeffding Tree Grace Period Tuning
- Heuristic:Risingwavelabs Risingwave LSM Compaction Tuning
- Heuristic:SqueezeAILab ETS Max Depth And Token Guards
- Heuristic:Eventual Inc Daft Execution Config Tuning
- Heuristic:CarperAI Trlx Partial Layer Freezing
- Heuristic:Microsoft DeepSpeedExamples RLHF Hyperparameter Guide
- Heuristic:Apache Spark Serialization Optimization
Environments
- Environment:ARISE Initiative Robosuite GPU Rendering
- Environment:Microsoft Onnxruntime CUDA GPU Environment
- Environment:LLMBook zh LLMBook zh github io PyTorch CUDA GPU Environment
- Environment:Huggingface Optimum GPTQ Quantization Environment
- Environment:Avdvg InjectGuard CUDA GPU
- Environment:Langchain ai Langgraph Python Runtime Environment
- Environment:Zai org CogVideo Diffusers Inference Environment
- Environment:Mlflow Mlflow Python Runtime Environment
- Environment:Obss Sahi Python Image Processing
- Environment:Ray project Ray Docker GPU Environment