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:Obss Sahi COCO Dataset Slicing
- Workflow:TobikoData Sqlmesh Github CICD automation
- Workflow:Turboderp org Exllamav2 EXL2 Model Conversion
- Workflow:Shiyu coder Kronos CSV Finetuning
- Workflow:Spcl Graph of thoughts GoT Keyword Counting Pipeline
- Workflow:Anthropics Anthropic sdk python Streaming Message Interaction
- Workflow:Scikit learn Scikit learn Hyperparameter Tuning
- Workflow:Helicone Helicone LLM Request Proxy Logging
- Workflow:Lm sys FastChat Vicuna SFT Finetuning
- Workflow:Microsoft BIPIA Attack Success Rate Evaluation
Principles
- Principle:AnswerDotAI RAGatouille Index Loading
- Principle:Spcl Graph of thoughts Document Merging Prompt Design
- Principle:Shiyu coder Kronos Topk Dropout Portfolio Strategy
- Principle:OpenRLHF OpenRLHF Process Reward Dataset Construction
- Principle:Microsoft Onnxruntime ONNX Input Schema Definition
- Principle:Huggingface Peft Prefix Tuning
- Principle:Tensorflow Serving HTTP Compression
- Principle:Apache Druid Publication Settings
- Principle:Microsoft Agent framework Azure Chat Client Configuration
- Principle:FMInference FlexLLMGen Checkpoint Format Abstraction
Implementations
- Implementation:Interpretml Interpret AutoVisualizeProvider
- Implementation:Bitsandbytes foundation Bitsandbytes Quantize 4bit
- Implementation:NVIDIA DALI DynamicScratchpad
- Implementation:Pytorch Serve Mnist Response Data
- Implementation:SeleniumHQ Selenium HasLaunchApp
- Implementation:Lm sys FastChat Split Train Test
- Implementation:Rapidsai Cuml Boston Dataset
- Implementation:Avhz RustQuant KNearestNeighbors
- Implementation:LaurentMazare Tch rs Tokenizer From File
- Implementation:Online ml River Metrics Recall
Heuristics
- Heuristic:Ggml org Llama cpp Quantization Quality Tips
- Heuristic:Allenai Open instruct Warning Archived Dev Scripts
- Heuristic:Openai Whisper Compression Ratio Threshold
- Heuristic:Evidentlyai Evidently Column Type Inference Rules
- Heuristic:Webdriverio Webdriverio Stale Element Auto Refetch
- Heuristic:Romsto Speculative Decoding Ngram Order Selection
- Heuristic:Pytorch Serve CPU Performance Tuning
- Heuristic:Marker Inc Korea AutoRAG Passage Filter Safety Minimum
- Heuristic:LLMBook zh LLMBook zh github io LoRA Initialization Strategy
- Heuristic:Risingwavelabs Risingwave Docker Memory Allocation
Environments
- Environment:Online ml River Build Toolchain
- Environment:Mistralai Client python Realtime Transcription Environment
- Environment:Run llama Llama index Fsspec Remote Storage
- Environment:Alibaba ROLL ROCm GPU Environment
- Environment:Princeton nlp SimPO VLLM Inference
- Environment:Kubeflow Kubeflow Python KFP SDK Environment
- Environment:Pytorch Serve vLLM Engine Environment
- Environment:Mbzuai oryx Awesome LLM Post training Python Matplotlib
- Environment:Spotify Luigi Hadoop HDFS Cluster
- Environment:Langgenius Dify Python Backend Environment