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:EvolvingLMMs Lab Lmms eval Custom Task Creation
- Workflow:MarketSquare Robotframework browser JavaScript Extension
- Workflow:Romsto Speculative Decoding Ngram Assisted Speculative Decoding
- Workflow:HKUDS AI Trader Data Pipeline
- Workflow:Sgl project Sglang Multimodal Vision Language Inference
- Workflow:ChenghaoMou Text dedup Bloom Filter Deduplication
- Workflow:Protectai Modelscan Custom Scanner Plugin
- Workflow:Datajuicer Data juicer Dataset Quality Analysis
- Workflow:Iamhankai Forest of Thought FoT Benchmark Evaluation
- Workflow:FMInference FlexLLMGen HELM Benchmark Evaluation
Principles
- Principle:Scikit learn contrib Imbalanced learn Synthetic Minority Oversampling
- Principle:Getgauge Taiko Browser Launch
- Principle:Langgenius Dify Indexing Method Selection
- Principle:ContextualAI HALOs Reward Model Configuration
- Principle:DevExpress Testcafe Browser Provider Selection
- Principle:Microsoft Onnxruntime ONNX Input Schema Definition
- Principle:Allenai Open instruct Model Publishing
- Principle:Spotify Luigi Spark Job Definition
- Principle:Promptfoo Promptfoo Attack Generation
- Principle:Bitsandbytes foundation Bitsandbytes 4bit Quantization Configuration
Implementations
- Implementation:Lm sys FastChat Summarize Cluster
- Implementation:Online ml River Linear Model ALMAClassifier
- Implementation:Huggingface Datasets Dataset To Csv
- Implementation:Heibaiying BigData Notes WordCountReducer Reduce
- Implementation:Obss Sahi Visualize Object Predictions
- Implementation:Microsoft Onnxruntime OrtUtil
- Implementation:Apache Druid SchemaColumnList
- Implementation:ARISE Initiative Robosuite JointVelocityController
- Implementation:Guardrails ai Guardrails Guard Call Stream
- Implementation:Helicone Helicone UseProFeature
Heuristics
- Heuristic:Tensorflow Tfjs WebGL Shader Warmup
- Heuristic:Microsoft DeepSpeedExamples Gradient Checkpointing Tradeoff
- Heuristic:Deepspeedai DeepSpeed FP16 Convergence Tips
- Heuristic:Microsoft Agent framework Declaration Only Tools Pattern
- Heuristic:InternLM Lmdeploy Max Batch Size Selection
- Heuristic:AUTOMATIC1111 Stable diffusion webui VRAM Management Strategies
- Heuristic:Wandb Weave Sentinel Value Handling
- Heuristic:Facebookresearch Audiocraft Audio Normalization Strategies
- Heuristic:Sdv dev SDV HMA Schema Simplification
- Heuristic:Dagster io Dagster Record Over Dataclass
Environments
- Environment:Princeton nlp SimPO VLLM Inference
- Environment:Intel Ipex llm Build Environment
- Environment:Mlc ai Mlc llm Metal macOS iOS Environment
- Environment:PacktPublishing LLM Engineers Handbook VLLM Evaluation Environment
- Environment:Togethercomputer Together python Fine Tuning Data Requirements
- Environment:Datahub project Datahub Spark Lineage Environment
- Environment:Run llama Llama index Python LlamaIndex Core
- Environment:Ggml org Ggml C Cpp Build Environment
- Environment:Mistralai Client python Realtime Transcription Environment
- Environment:Mlc ai Mlc llm TVM Runtime Environment