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:Vllm project Vllm Speculative Decoding
- Workflow:Ollama Ollama Model Pull And Run
- Workflow:Teamcapybara Capybara Selenium Driver Configuration
- Workflow:Facebookresearch Audiocraft JASCO Conditioned Music Generation
- Workflow:Gretelai Gretel synthetics ACTGAN Tabular Synthesis
- Workflow:DevExpress Testcafe Basic Test Authoring
- Workflow:Anthropics Anthropic sdk python Extended Thinking Reasoning
- Workflow:Ggml org Llama cpp HF to GGUF Model Conversion
- Workflow:Zai org CogVideo Diffusers Text to Video Inference
- Workflow:Isaac sim IsaacGymEnvs Policy Inference and Evaluation
Principles
- Principle:Kserve Kserve Canary Deployment Initialization
- Principle:Microsoft Onnxruntime Trained Model Export
- Principle:Spcl Graph of thoughts Keyword Counting Prompt Design
- Principle:Huggingface Datasets DatasetDict Hub Upload
- Principle:Webdriverio Webdriverio UtilityPattern
- Principle:Princeton nlp Tree of thought llm Naive Baseline Sampling
- Principle:Lm sys FastChat MT Bench Answer Generation
- Principle:Langfuse Langfuse S3 Payload Upload
- Principle:TA Lib Ta lib python Pattern Signal Interpretation
- Principle:Alibaba MNN Winograd Kernel Codegen
Implementations
- Implementation:Microsoft Onnxruntime Fp16Conversions JVM
- Implementation:Datajuicer Data juicer DWposeDetector
- Implementation:Alibaba MNN FlatBuffers Flatc
- Implementation:Helicone Helicone Auth Config
- Implementation:Triton inference server Server InferUtil
- Implementation:Hiyouga LLaMA Factory SFT Metric
- Implementation:Ggml org Llama cpp Chat Parser Header
- Implementation:Dotnet Machinelearning LdaHybridMap
- Implementation:Mlc ai Mlc llm Dynamic Bitset
- Implementation:Mistralai Client python Ocr Process
Heuristics
- Heuristic:Junyanz Pytorch CycleGAN and pix2pix High Res Crop Training
- Heuristic:Risingwavelabs Risingwave Source Backoff Strategy
- Heuristic:Openai Openai python Warning Deprecated Legacy Response
- Heuristic:Farama Foundation Gymnasium Seeding Determinism Best Practices
- Heuristic:FMInference FlexLLMGen Weight Compression 4bit
- Heuristic:InternLM Lmdeploy Max Batch Size Selection
- Heuristic:Fastai Fastbook Mixup Data Augmentation
- Heuristic:Sgl project Sglang Schedule Conservativeness Tuning
- Heuristic:Langgenius Dify Celery Queue Separation
- Heuristic:Openai Whisper SDPA Disabling For Attention Extraction
Environments
- Environment:Deepset ai Haystack HuggingFace Model Environment
- Environment:Vllm project Vllm AMD ROCm
- Environment:Vllm project Vllm Environment Variables
- Environment:Google deepmind Mujoco MJX Warp CUDA Environment
- Environment:Lm sys FastChat SFT Training Environment
- Environment:MaterializeInc Materialize Dbt Materialize Runtime
- Environment:Treeverse LakeFS S3 Gateway Test Environment
- Environment:SeldonIO Seldon core Kafka Messaging Environment
- Environment:Unstructured IO Unstructured Profiling Tools
- Environment:Princeton nlp SimPO VLLM Inference