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:Mistralai Client python Chat Completion
- Workflow:TA Lib Ta lib python Streaming Indicator Computation
- Workflow:Langfuse Langfuse Prompt management lifecycle
- Workflow:Heibaiying BigData Notes Hive Data Warehouse Operations
- Workflow:Princeton nlp Tree of thought llm Adding new task
- Workflow:Huggingface Peft LoRA Causal LM Finetuning
- Workflow:Huggingface Datasets Format Conversion
- Workflow:ArroyoSystems Arroyo Connection Setup
- Workflow:Eventual Inc Daft Multimodal AI Batch Inference
- Workflow:Datahub project Datahub Metadata Actions Pipeline
Principles
- Principle:MaterializeInc Materialize Upgrade Scenario Execution
- Principle:Evidentlyai Evidently LLM Judge Evaluation
- Principle:Diagram of thought Diagram of thought Prompt Template Selection
- Principle:Ggml org Llama cpp AdapterSupport
- Principle:Openai Openai node File Processing Verification
- Principle:Openai Openai python Realtime Conversation Management
- Principle:Isaac sim IsaacGymEnvs Factory Scene Initialization
- Principle:Datajuicer Data juicer Ray Cluster Initialization
- Principle:Webdriverio Webdriverio Driver Management
- Principle:ArroyoSystems Arroyo Job State Machine
Implementations
- Implementation:Tensorflow Tfjs CenterCrop Layer
- Implementation:Intel Ipex llm Deepspeed AutoTP FastAPI Serving
- Implementation:Rapidsai Cuml Manifold Common
- Implementation:NVIDIA NeMo Curator MarkdownRemover
- Implementation:Pytorch Serve Accelerate Handler
- Implementation:Open compass VLMEvalKit VGRPBench Renzoku
- Implementation:Microsoft Onnxruntime ExportModelForInferencing Distributed
- Implementation:Ggml org Ggml Webgpu backend
- Implementation:Puppeteer Puppeteer Website Package Lock
- Implementation:Ggml org Llama cpp Common Header
Heuristics
- Heuristic:Anthropics Anthropic sdk python Model Deprecation Awareness
- Heuristic:Spotify Luigi Dynamic Requirements Generator
- Heuristic:Microsoft Onnxruntime Flash Attention Optimization
- Heuristic:Risingwavelabs Risingwave Source Backoff Strategy
- Heuristic:Iamhankai Forest of Thought Early Stop Majority Vote
- Heuristic:LLMBook zh LLMBook zh github io IGNORE INDEX Loss Masking
- Heuristic:Huggingface Alignment handbook Global Batch Size Scaling
- Heuristic:Google research Deduplicate text datasets Ulimit File Descriptors For Merge
- Heuristic:Deepseek ai Janus Bfloat16 Operation Workarounds
- Heuristic:Openai Openai agents python Default Max Turns Safety Limit
Environments
- Environment:Pyro ppl Pyro Distributed Training
- Environment:Eventual Inc Daft Cloud Storage Credentials
- Environment:Shiyu coder Kronos DDP Multi GPU Environment
- Environment:Apache Hudi Docker Demo Environment
- Environment:CrewAIInc CrewAI LLM Provider Credentials
- Environment:Alibaba ROLL Python Runtime Environment
- Environment:Datahub project Datahub Docker Runtime
- Environment:Sgl project Sglang Kubernetes
- Environment:NVIDIA NeMo Aligner TensorRT LLM Acceleration Environment
- Environment:Mage ai Mage ai Python 3 9 Runtime