Main Page: Difference between revisions
Random page shuffling with NOCACHE |
Update plugin descriptions, add Kapso |
||
| (2 intermediate revisions by 2 users not shown) | |||
| Line 32: | Line 32: | ||
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. | 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 | '''Connect your AI coding agent.''' Plug Leeroopedia into your favorite coding agent, and let it build robust AI/ML systems autonomously: | ||
''' | * [https://github.com/Leeroo-AI/superml '''SuperML plugin'''] — converts your AI coding agent into an expert ML engineer with agentic memory | ||
* [https://github.com/Leeroo-AI/leeroopedia-mcp '''Leeroopedia MCP'''] — search over best-practices and skills of ML/AI | |||
* [https://github.com/leeroo-ai/kapso '''Kapso'''] — experimentation platform for autonomous AI/ML software building | |||
== Browse by Category == | == Browse by Category == | ||
| Line 54: | Line 56: | ||
== Explore Pages == | == Explore Pages == | ||
=== Workflows === | === Workflows === | ||
Latest revision as of 11:45, 14 March 2026
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:PacktPublishing LLM Engineers Handbook Dataset Generation
- Workflow:Risingwavelabs Risingwave CDC Data Replication
- Workflow:Infiniflow Ragflow Chat Application Setup
- Workflow:TobikoData Sqlmesh Model development and testing
- Workflow:Ggml org Llama cpp Model Quantization
- Workflow:Apache Paimon Lance Format Analytics
- Workflow:Isaac sim IsaacGymEnvs Domain Randomization Training
- Workflow:Tencent Ncnn Vulkan GPU Accelerated Inference
- Workflow:Hiyouga LLaMA Factory LoRA SFT Finetuning
- Workflow:Ucbepic Docetl Long Document Chunking
Principles
- Principle:Wandb Weave Prompt Retrieval
- Principle:Eventual Inc Daft CSV Writing
- Principle:Puppeteer Puppeteer Browser Process Management
- Principle:Microsoft BIPIA Tokenizer And Model Preparation
- Principle:Dagster io Dagster Dbt Project Integration
- Principle:Huggingface Datatrove Language Identification
- Principle:Kserve Kserve Disaggregated Deployment
- Principle:Guardrails ai Guardrails Observability Configuration
- Principle:Vespa engine Vespa Version Preparation
- Principle:Pola rs Polars Streaming Data Scanning
Implementations
- Implementation:NVIDIA DALI Operator Trace Tests
- Implementation:MaterializeInc Materialize Mkpipeline Sh
- Implementation:Microsoft LoRA WebNLG Train Dataset
- Implementation:Togethercomputer Together python Speech Create
- Implementation:Puppeteer Puppeteer Mutex
- Implementation:Iterative Dvc Plan Repro
- Implementation:Lance format Lance FilterPlanner
- Implementation:Google deepmind Dm control Manipulation Load
- Implementation:Mit han lab Llm awq LlavaMetaForCausalLM
- Implementation:Ggml org Llama cpp Vocab Header
Heuristics
- Heuristic:Vespa engine Vespa Log Level Inheritance Polling
- Heuristic:Marker Inc Korea AutoRAG Batch Size Tuning
- Heuristic:LLMBook zh LLMBook zh github io LoRA Initialization Strategy
- Heuristic:MarketSquare Robotframework browser MacOS Sonoma Startup Delay
- Heuristic:Apache Flink Async Sink Timeout And Backpressure Defaults
- Heuristic:Confident ai Deepeval Dotenv Loading Order
- Heuristic:Ggml org Llama cpp GPU Layer Offloading Verification
- Heuristic:Tencent Ncnn Optimize Before Quantize
- Heuristic:MaterializeInc Materialize CI Agent Prioritization
- Heuristic:Astronomer Astronomer cosmos Watcher Queue Sizing
Environments
- Environment:Openclaw Openclaw Node 22 Runtime
- Environment:Ggml org Ggml C Cpp Build Environment
- Environment:Apache Kafka JVM Runtime Environment
- Environment:Getgauge Taiko Linux System Libraries
- Environment:Vllm project Vllm Buildkite
- Environment:NVIDIA NeMo Curator Ray Cluster
- Environment:Hiyouga LLaMA Factory FP8 Training Environment
- Environment:Sgl project Sglang Runtime
- Environment:Microsoft LoRA NLU Conda Environment
- Environment:Sgl project Sglang OpenAI