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:Mlc ai Mlc llm REST API Serving
- Workflow:MarketSquare Robotframework browser Plugin Development
- Workflow:Getgauge Taiko Network Request Interception
- Workflow:Haotian liu LLaVA LoRA Finetuning
- Workflow:Bentoml BentoML Model Store Management
- Workflow:Langfuse Langfuse Batch export pipeline
- Workflow:Mage ai Mage ai API Source Extraction
- Workflow:Getgauge Taiko Headless Browser Testing
- Workflow:Run llama Llama index Evaluation Pipeline
- Workflow:Truera Trulens RAG Evaluation With LangChain
Principles
- Principle:Huggingface Datasets Dataset Sorting
- Principle:Tensorflow Serving Server Configuration And Startup
- Principle:Datajuicer Data juicer Data Export
- Principle:Duckdb Duckdb Package Validation
- Principle:Haosulab ManiSkill Task Space Control
- Principle:Langgenius Dify PaymentIntegration
- Principle:Triton inference server Server HTTP Server Architecture
- Principle:Ray project Ray Application Deployment
- Principle:Apache Hudi Compaction Commit
- Principle:Mit han lab Llm awq Activation Aware Weight Quantization
Implementations
- Implementation:Openai Openai node Beta RealtimeWebSocket
- Implementation:Axolotl ai cloud Axolotl Merge Fsdp Weights
- Implementation:Evidentlyai Evidently Legacy IsValidJSON Feature
- Implementation:Nightwatchjs Nightwatch Custom Assertion Interface
- Implementation:Vllm project Vllm LLM Get Metrics
- Implementation:Gretelai Gretel synthetics DataFrameBatch Create Training Data
- Implementation:Mlflow Mlflow Log Assessment
- Implementation:ClickHouse ClickHouse Clickhouse Server Start
- Implementation:Promptfoo Promptfoo Version Constants
- Implementation:Vllm project Vllm CPU Types VXE
Heuristics
- Heuristic:ChenghaoMou Text dedup Bloom Filter Single Process
- Heuristic:Deepset ai Haystack Document Splitting Defaults
- Heuristic:Protectai Modelscan Graceful Scanner Degradation
- Heuristic:OWASP Www project top 10 for large language model applications Deliberately Insecure Code Isolation
- Heuristic:Vibrantlabsai Ragas Warning Deprecated V1 Metrics
- Heuristic:Mlfoundations Open flamingo RICES Feature Caching
- Heuristic:Unstructured IO Unstructured Golden File Diff
- Heuristic:Microsoft Agent framework Tool Approval Mode Production
- Heuristic:Eric mitchell Direct preference optimization FSDP Batch Size Per GPU
- Heuristic:Langfuse Langfuse ClickHouse FINAL Skip Optimization
Environments
- Environment:Wandb Weave Python SDK Runtime
- Environment:Microsoft DeepSpeedExamples ZeRO Inference Runtime
- Environment:Ggml org Ggml C Cpp Build Environment
- Environment:Webdriverio Webdriverio Browser Driver Environment
- Environment:Togethercomputer Together python API Credentials
- Environment:Risingwavelabs Risingwave Java Connector Environment
- Environment:Testtimescaling Testtimescaling github io GitHub Actions Runner
- Environment:Nautechsystems Nautilus trader Databento API Credentials
- Environment:Lakeraai Pint benchmark Python 310 With Pandas
- Environment:Togethercomputer Together python Python SDK Runtime