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:Protectai Modelscan CLI Model Scanning
- Workflow:Datahub project Datahub Protobuf Schema Ingestion
- Workflow:Datahub project Datahub Java SDK V2 Entity Management
- Workflow:Confident ai Deepeval LLM Tracing and Observability
- Workflow:Microsoft Agent framework Basic Agent Creation
- Workflow:Google research Deduplicate text datasets Suffix array querying
- Workflow:Ggml org Llama cpp OpenAI Compatible Server
- Workflow:Vespa engine Vespa Linguistics text processing pipeline
- Workflow:Dagster io Dagster DSPy Optimization
- Workflow:Run llama Llama index OpenAI LLM Finetuning
Principles
- Principle:Marker Inc Korea AutoRAG Strategy Based Module Selection
- Principle:Microsoft Playwright Test Execution and Reporting
- Principle:Ggml org Llama cpp PresetConfiguration
- Principle:Turboderp org Exllamav2 Dataset Loading
- Principle:Mistralai Client python Client Initialization
- Principle:Bitsandbytes foundation Bitsandbytes Mixed Precision Matmul With Outlier Decomposition
- Principle:Webdriverio Webdriverio W3CProtocolCompliance
- Principle:SeldonIO Seldon core V2 Inference Protocol
- Principle:Duckdb Duckdb Executable Building
- Principle:Webdriverio Webdriverio Environment Detection
Implementations
- Implementation:Mit han lab Llm awq InternVL Benchmark
- Implementation:Spotify Luigi OpenerTarget
- Implementation:Teamcapybara Capybara Spec Shared Matchers
- Implementation:Infiniflow Ragflow File Util
- Implementation:Norrrrrrr lyn WAInjectBench try wrap lora
- Implementation:Google deepmind Mujoco mjCModel Compile
- Implementation:Online ml River Stream Cache
- Implementation:Huggingface Transformers Pipeline Function
- Implementation:LaurentMazare Tch rs VecGymEnv
- Implementation:NVIDIA NeMo Curator Metrics Utils
Heuristics
- Heuristic:DevExpress Testcafe Browser Connection Timeouts
- Heuristic:Deepset ai Haystack BM25 Score Scaling
- Heuristic:Rapidsai Cuml Batch Size Memory Tradeoff
- Heuristic:Pola rs Polars GPU Aggregation Join Speedup
- Heuristic:Kubeflow Pipelines Cache Staleness In Recursive Pipelines
- Heuristic:Pola rs Polars Streaming For Large Datasets
- Heuristic:Fede1024 Rust rdkafka Sensitive Config Sanitization
- Heuristic:Ray project Ray Serve Concurrency And Backpressure
- Heuristic:Ggml org Llama cpp Thread Count Tuning
- Heuristic:Unstructured IO Unstructured Hi Res Model Configuration
Environments
- Environment:Apache Beam Java Build Environment
- Environment:LLMBook zh LLMBook zh github io HuggingFace Transformers Stack
- Environment:Ggml org Ggml C Cpp Build Environment
- Environment:Microsoft BIPIA Python CUDA GPU Environment
- Environment:Google deepmind Mujoco MJX Warp CUDA Environment
- Environment:Deepset ai Haystack OpenAI API Environment
- Environment:Openai Whisper Numba
- Environment:TobikoData Sqlmesh Dbt Compatibility
- Environment:NVIDIA NeMo Aligner PyTriton Serving Environment
- Environment:OpenRLHF OpenRLHF Ray Distributed Environment