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:Mlc ai Web llm Function Calling
- Workflow:Haifengl Smile Data Loading Pipeline
- Workflow:PacktPublishing LLM Engineers Handbook LLM Finetuning
- Workflow:LaurentMazare Tch rs JIT Model Inference
- Workflow:Bigscience workshop Petals Server Contribution
- Workflow:Promptfoo Promptfoo LLM Evaluation
- Workflow:Google deepmind Dm control Manipulation Task Setup
- Workflow:Avhz RustQuant Yield Curve Construction
- Workflow:Webdriverio Webdriverio Cloud Service Integration
- Workflow:Bentoml BentoML BentoCloud Deployment
Principles
- Principle:Danijar Dreamerv3 Agent Initialization
- Principle:Vllm project Vllm Multi LoRA Request Routing
- Principle:FlagOpen FlagEmbedding LLM Representation Learning
- Principle:Huggingface Alignment handbook LoRA Adapter Configuration
- Principle:Kubeflow Kubeflow Component Deployment
- Principle:FlowiseAI Flowise Workspace Navigation
- Principle:Langgenius Dify Model and Prompt Configuration
- Principle:Ggml org Llama cpp Conversion Verification
- Principle:AUTOMATIC1111 Stable diffusion webui Application Lifecycle
- Principle:Bentoml BentoML API Endpoint Definition
Implementations
- Implementation:TA Lib Ta lib python Build TA Lib C
- Implementation:Tensorflow Tfjs Tensorflowjs Pip Install
- Implementation:Protectai Llm guard Input BanSubstrings
- Implementation:Bentoml BentoML SDK Validators
- Implementation:Haosulab ManiSkill Stompy
- Implementation:Tensorflow Serving Tfrt Multi Inference Test
- Implementation:Lucidrains X transformers FreeTransformer
- Implementation:ArroyoSystems Arroyo Jobs Api
- Implementation:Obss Sahi Pyproject Configuration
- Implementation:TA Lib Ta lib python TA Initialize Shutdown
Heuristics
- Heuristic:Junyanz Pytorch CycleGAN and pix2pix Batch Size One Default
- Heuristic:Huggingface Diffusers Guidance Scale Defaults
- Heuristic:Elevenlabs Elevenlabs python TTS Model Selection
- Heuristic:Apache Airflow Memory Management Tips
- Heuristic:Princeton nlp SimPO Dropout Disabling
- Heuristic:Tencent Ncnn Optimize Before Quantize
- Heuristic:ContextualAI HALOs TF32 Matmul Acceleration
- Heuristic:Evidentlyai Evidently Statistical Test Auto Selection
- Heuristic:Apache Beam Warning Deprecated Twister2 Runner
- Heuristic:FlagOpen FlagEmbedding Dynamic Batch Size Reduction
Environments
- Environment:Sgl project Sglang CPU Runtime
- Environment:Run llama Llama index Sentence Transformers Finetuning
- Environment:EvolvingLMMs Lab Lmms eval GPU Compute Environment
- Environment:Datahub project Datahub Java 17 Backend Environment
- Environment:NVIDIA NeMo Curator Python Linux Base
- Environment:Mlc ai Web llm Node Build Toolchain
- Environment:Heibaiying BigData Notes Spark 2 4 Environment
- Environment:Sgl project Sglang Python Dependencies
- Environment:ThreeSR Awesome Inference Time Scaling Python Runtime Environment
- Environment:Allenai Open instruct Beaker Cluster