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:Microsoft Semantic kernel Agent Conversation And Orchestration
- Workflow:Protectai Llm guard Scanner Benchmarking
- Workflow:Ray project Ray Cross Language Invocation
- Workflow:Kserve Kserve Deploying InferenceService
- Workflow:Sgl project Sglang Offline Batch Inference
- Workflow:Elevenlabs Elevenlabs python Text to Speech Generation
- Workflow:Huggingface Peft QLoRA SFT Finetuning
- Workflow:Heibaiying BigData Notes Hive Data Warehouse Operations
- Workflow:Langchain ai Langgraph Building a Stateful Graph
- Workflow:Cleanlab Cleanlab Multiannotator Consensus
Principles
- Principle:Microsoft Semantic kernel Vector Similarity Search
- Principle:BerriAI Litellm Database Setup
- Principle:Getgauge Taiko Code Generation
- Principle:Google research Deduplicate text datasets Dataset Serialization HF
- Principle:Apache Druid Partitioning Configuration
- Principle:Avhz RustQuant Curve Interpolation
- Principle:Helicone Helicone Provider Key Management
- Principle:ARISE Initiative Robosuite Lighting Randomization
- Principle:Microsoft Semantic kernel AI Service Registration
- Principle:HKUDS AI Trader Frontend Cache Generation
Implementations
- Implementation:Microsoft DeepSpeedExamples HelloDeepSpeed Train Bert DS
- Implementation:Unslothai Unsloth Save Pretrained GGUF
- Implementation:Online ml River Stream Iter Libsvm
- Implementation:Ggml org Ggml Webgpu backend
- Implementation:Tensorflow Tfjs GraphModel Predict
- Implementation:Google deepmind Dm control Reference Pose Utils
- Implementation:Lance format Lance CommitHandler
- Implementation:Datajuicer Data juicer SentenceSplitMapper
- Implementation:Truera Trulens Compare Tab
- Implementation:FlagOpen FlagEmbedding MLVU Sub Scene Data
Heuristics
- Heuristic:Huggingface Trl QLoRA BF16 Adapter Casting
- Heuristic:Neuml Txtai Faiss Index Sizing Tip
- Heuristic:Vespa engine Vespa Warning Deprecated Cloud API Constructors
- Heuristic:Fede1024 Rust rdkafka Cooperative Rebalance Protocol
- Heuristic:Risingwavelabs Risingwave LSM Compaction Tuning
- Heuristic:MaterializeInc Materialize CI Agent Prioritization
- Heuristic:Onnx Onnx Big Endian Byte Order Handling
- Heuristic:Google deepmind Dm control Prop Settling Physics Tuning
- Heuristic:PeterL1n BackgroundMattingV2 Mixed Precision Training
- Heuristic:NVIDIA NeMo Aligner PPO Critic Warmup Tip
Environments
- Environment:Mage ai Mage ai Singer SDK And Joblib Runtime
- Environment:DataExpert io Data engineer handbook Spark Iceberg Docker Environment
- Environment:Avhz RustQuant Rust Stable
- Environment:Tensorflow Serving Docker Runtime Environment
- Environment:Unslothai Unsloth Python Transformers
- Environment:Kornia Kornia PyTorch Python Environment
- Environment:Tencent Ncnn Build Environment
- Environment:Heibaiying BigData Notes Flink 1 9 Environment
- Environment:Duckdb Duckdb Release Publishing Env
- Environment:Rapidsai Cuml CUDA GPU