Performance vs Practicality: A Comparison of vLLM and OllamavLLM is designed for high-throughput scenarios, while Ollama emphasizes day-to-day simplicity and good-enough performance for most use…May 27A response icon1May 27A response icon1
From Unstructured Text to Interactive Knowledge Graphs Using LLMsHow LLMs can used in a knowledge extraction and visualization pipelineMar 30A response icon30Mar 30A response icon30
EyerisAI: Intelligent Visual Event Detection & Response SystemA Project Uniting Cameras, Computer Vision, and AI to Observe, Detect, Log and Respond in Real TimeFeb 19A response icon1Feb 19A response icon1
Inside the Private Thoughts of AIHow DeepSeek’s Inner Monologue Redefines What We Expect From Language ModelsFeb 10A response icon1Feb 10A response icon1
From Likes to Language ModelsThe Culture Industry Revisited in the Age of Algorithmic CivilizationJan 27Jan 27
Elevating the Human-Computer Interface Through Mechanical KeyboardsMy Journey and Comprehensive Introduction to Mechanical KeyboardsJan 21Jan 21
Technology Governance with Architecture PrinciplesBridging High-Level Strategy and Day-to-Day Technology DecisionsDec 30, 2024A response icon2Dec 30, 2024A response icon2
Centralizing Multi-Vendor LLM Services with LiteLLMCreating a single OpenAI compatible API endpoint with access to models from OpenAI, Azure, Google, Anthropic, AWS and more.Dec 16, 2024A response icon2Dec 16, 2024A response icon2
Large Scale Batch Processing with OllamaCreating a self-hosted batch prompt processing cluster using OllamaNov 25, 2024A response icon5Nov 25, 2024A response icon5
Published inCubedLLM Zero-to-Hero with OllamaSetup your own private Generative AI environment using OllamaOct 22, 2024Oct 22, 2024
