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:Openai CLIP Linear probe evaluation
- Workflow:Truera Trulens Snowflake Observability Pipeline
- Workflow:Marker Inc Korea AutoRAG Data Creation Pipeline
- Workflow:BerriAI Litellm Response Caching
- Workflow:InternLM Lmdeploy W4A16 AWQ Quantization
- Workflow:Ucbepic Docetl Playground Interactive Development
- Workflow:Huggingface Datasets Hub Publishing
- Workflow:Tencent Ncnn PyTorch Model Conversion and Inference
- Workflow:Openai Openai python Realtime Conversation
- Workflow:Openclaw Openclaw Multi Agent Routing
Principles
- Principle:Arize ai Phoenix LLM Provider Configuration
- Principle:LLMBook zh LLMBook zh github io High Throughput LLM Inference
- Principle:Apache Spark Source Compilation
- Principle:TA Lib Ta lib python Cython Binding Generation
- Principle:Romsto Speculative Decoding Input Tokenization
- Principle:Huggingface Datatrove WARC Archive Reading
- Principle:Mlc ai Web llm Page Content Access
- Principle:Neuml Txtai Agent Task Execution
- Principle:Huggingface Transformers CI Notification And Reporting
- Principle:Eventual Inc Daft Data Ingestion HuggingFace
Implementations
- Implementation:Duckdb Duckdb Brotli Encoder
- Implementation:CARLA simulator Carla Start Replaying Tool
- Implementation:Sgl project Sglang GGUF Quantization
- Implementation:MaterializeInc Materialize CLI Orchestratord
- Implementation:Open compass VLMEvalKit OmChat
- Implementation:Tensorflow Serving static source router h
- Implementation:Pytorch Serve Benchmark
- Implementation:Kubeflow Kubeflow Label Bot Stale Bot Config
- Implementation:Google deepmind Dm control Composer Environment
- Implementation:Haifengl Smile DenseMatrix Decomposition
Heuristics
- Heuristic:Vllm project Vllm Attention Backend Selection
- Heuristic:NVIDIA NeMo Aligner PPO Critic Warmup Tip
- Heuristic:Ggml org Llama cpp Quantization Quality Tips
- Heuristic:Cleanlab Cleanlab Confident Threshold Heuristic
- Heuristic:Openai Openai agents python MCP Server Lifecycle Management
- Heuristic:Kserve Kserve Prefix Cache Consistency
- Heuristic:LLMBook zh LLMBook zh github io Greedy Decoding Temperature Zero
- Heuristic:Neuml Txtai Faiss Index Sizing Tip
- Heuristic:CrewAIInc CrewAI MCP Timeout And Retry Strategy
- Heuristic:Axolotl ai cloud Axolotl FSDP Configuration Guide
Environments
- Environment:BerriAI Litellm Provider API Credentials
- Environment:Bitsandbytes foundation Bitsandbytes ROCm AMD Environment
- Environment:Apache Druid Druid Operator Kubernetes
- Environment:Microsoft Playwright Platform Support Environment
- Environment:Apache Dolphinscheduler Node Pnpm Runtime
- Environment:CrewAIInc CrewAI Optional Provider Dependencies
- Environment:MarketSquare Robotframework browser Node Runtime
- Environment:Gretelai Gretel synthetics PyTorch CUDA Environment
- Environment:Langfuse Langfuse PostgreSQL 17
- Environment:Datajuicer Data juicer GPU CUDA Environment