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:Mit han lab Llm awq TinyChat LLM Deployment
- Workflow:Lm sys FastChat Vicuna SFT Finetuning
- Workflow:Sgl project Sglang ModelOpt Quantization And Export
- Workflow:ChenghaoMou Text dedup Benchmark Evaluation
- Workflow:AnswerDotAI RAGatouille ColBERT Training
- Workflow:LaurentMazare Tch rs Transfer Learning
- Workflow:Elevenlabs Elevenlabs python Speech to Text Transcription
- Workflow:Microsoft DeepSpeedExamples SuperOffload Finetuning
- Workflow:Langgenius Dify RAG Pipeline Development
- Workflow:Dagster io Dagster Modal Serverless Pipeline
Principles
- Principle:NVIDIA NeMo Curator Text Cleaning and Normalization
- Principle:Vllm project Vllm Streaming Response Handling
- Principle:Haifengl Smile Nearest Neighbor Query
- Principle:BerriAI Litellm Error Handling
- Principle:Ggml org Llama cpp GGUFFormat
- Principle:Confident ai Deepeval OpenAI Agents Instrumentation
- Principle:Langgenius Dify Debug Console Testing
- Principle:Ggml org Llama cpp Model Download
- Principle:Turboderp org Exllamav2 Vision Tower Loading
- Principle:Ollama Ollama GGUF Model Conversion GptOss
Implementations
- Implementation:Duckdb Duckdb Brotli Platform
- Implementation:Volcengine Verl Split Placement PPO Entry
- Implementation:Langchain ai Langgraph Pregel Debug
- Implementation:Openai Openai python Realtime Calls Override
- Implementation:Tencent Ncnn Vulkan Header Fix
- Implementation:Hpcaitech ColossalAI GPT Judge
- Implementation:Pyro ppl Pyro CoalescentTimes
- Implementation:Dotnet Machinelearning FastTree SurplusMART Derivatives
- Implementation:Dagster io Dagster Dbt Asset Check Integration
- Implementation:ArroyoSystems Arroyo Wait For State
Heuristics
- Heuristic:Microsoft LoRA Scaling Factor Alpha Over R
- Heuristic:Axolotl ai cloud Axolotl Attention Mechanism Selection
- Heuristic:Apache Flink Bin Packing Complexity Guard
- Heuristic:Openclaw Openclaw Retry With Exponential Backoff
- Heuristic:Huggingface Datatrove Thundering Herd Prevention
- Heuristic:Marker Inc Korea AutoRAG Empty Result Fallback
- Heuristic:Obss Sahi Auto Slice Resolution
- Heuristic:Tencent Ncnn Lightmode Memory Optimization
- Heuristic:Turboderp org Exllamav2 Paged Cache Configuration
- Heuristic:Huggingface Datasets Flatten Indices Performance
Environments
- Environment:Cohere ai Cohere python Cohere API Credentials
- Environment:Langgenius Dify Docker Compose Environment
- Environment:NVIDIA DALI PyTorch Environment
- Environment:ClickHouse ClickHouse Systemd Runtime
- Environment:Huggingface Open r1 vLLM Server
- Environment:Bentoml BentoML BentoCloud Credentials
- Environment:Unslothai Unsloth Llama Cpp
- Environment:Teamcapybara Capybara Selenium WebDriver Environment
- Environment:Openai Whisper Triton
- Environment:Unslothai Unsloth CUDA VLLM