Updates and recent posts about vLLM..

Posts
Description

Activity

@cristiandeluxe started using tool Google GKE , 1 month ago.

Activity

@cristiandeluxe started using tool GNU/Linux , 1 month ago.

Activity

@cristiandeluxe started using tool Docker , 1 month ago.

Activity

@cristiandeluxe started using tool cPanel , 1 month ago.

Story

@laura_garcia shared a post, 1 month, 1 week ago

Software Developer, RELIANOID

RELIANOID Live Demo

Behind every successful deployment, there’s a 𝗱𝗲𝗱𝗶𝗰𝗮𝘁𝗲𝗱 𝘁𝗲𝗮𝗺 𝘄𝗼𝗿𝗸𝗶𝗻𝗴 𝗰𝗹𝗼𝘀𝗲𝗹𝘆 𝘄𝗶𝘁𝗵 𝗰𝘂𝘀𝘁𝗼𝗺𝗲𝗿𝘀 to 𝙙𝙚𝙡𝙞𝙫𝙚𝙧 𝙩𝙝𝙚 𝙧𝙞𝙜𝙝𝙩 𝙨𝙤𝙡𝙪𝙩𝙞𝙤𝙣 𝙖𝙩 𝙩𝙝𝙚 𝙧𝙞𝙜𝙝𝙩 𝙩𝙞𝙢𝙚. Today’s 𝗹𝗶𝘃𝗲 𝗱𝗲𝗺𝗼 𝘀𝗲𝘀𝘀𝗶𝗼𝗻 is a great example of how our engineers go beyond technology — providing 𝗵𝗮𝗻𝗱𝘀-𝗼𝗻 𝗲𝘅𝗽𝗲𝗿𝘁𝗶𝘀𝗲, 𝗿𝗲𝗮𝗹-𝘁𝗶𝗺𝗲 𝗴𝘂𝗶𝗱𝗮𝗻𝗰𝗲, and a 𝗳𝘂𝗹𝗹𝘆 𝗽𝗲𝗿𝘀𝗼𝗻𝗮..

Story

@laura_garcia shared a post, 1 month, 1 week ago

Software Developer, RELIANOID

𝗖𝗿𝗶𝘁𝗶𝗰𝗮𝗹 𝗖𝘆𝗯𝗲𝗿𝘀𝗲𝗰𝘂𝗿𝗶𝘁𝘆 𝗜𝗻𝗰𝗶𝗱𝗲𝗻𝘁𝘀 𝗶𝗻 𝘁𝗵𝗲 𝗜𝗻𝗱𝘂𝘀𝘁𝗿𝗶𝗮𝗹 𝗦𝗲𝗰𝘁𝗼𝗿

🚨 𝗖𝗿𝗶𝘁𝗶𝗰𝗮𝗹 𝗖𝘆𝗯𝗲𝗿𝘀𝗲𝗰𝘂𝗿𝗶𝘁𝘆 𝗜𝗻𝗰𝗶𝗱𝗲𝗻𝘁𝘀 𝗶𝗻 𝘁𝗵𝗲 𝗜𝗻𝗱𝘂𝘀𝘁𝗿𝗶𝗮𝗹 𝗦𝗲𝗰𝘁𝗼𝗿 🚨 According to recent industry reports, 2025 saw a significant rise in high-severity cyber incidents across critical sectors: 🔹 IT: 23% 🔹 Government: 18% 🔹 Industrial: 18% The industrial and food sectors are becoming increasingly attractive..

high-severity incident per industries graph

Activity

@sanjayaalpha859 started using tool Azure Pipelines , 1 month, 1 week ago.

Activity

@sanjayaalpha859 started using tool AccessTrade , 1 month, 1 week ago.

Story

@laura_garcia shared a post, 1 month, 1 week ago

Software Developer, RELIANOID

𝗗𝗲𝘃𝗗𝗮𝘆𝘀 • 𝗗𝗲𝘃𝗢𝗽𝘀 𝗣𝗿𝗼 • 𝗖𝘆𝗯𝗲𝗿𝗪𝗶𝘀𝗲𝗖𝗼𝗻 𝗘𝘂𝗿𝗼𝗽𝗲

🚀 𝗗𝗲𝘃𝗗𝗮𝘆𝘀 • 𝗗𝗲𝘃𝗢𝗽𝘀 𝗣𝗿𝗼 • 𝗖𝘆𝗯𝗲𝗿𝗪𝗶𝘀𝗲𝗖𝗼𝗻 𝗘𝘂𝗿𝗼𝗽𝗲 𝘛𝘩𝘳𝘦𝘦 𝘤𝘰𝘯𝘧𝘦𝘳𝘦𝘯𝘤𝘦𝘴. 𝘖𝘯𝘦 𝘦𝘤𝘰𝘴𝘺𝘴𝘵𝘦𝘮. 𝘜𝘯𝘭𝘪𝘮𝘪𝘵𝘦𝘥 𝘪𝘯𝘯𝘰𝘷𝘢𝘵𝘪𝘰𝘯. From May 19–22, 2026, 𝗥𝗘𝗟𝗜𝗔𝗡𝗢𝗜𝗗 will join the unified experience of 𝗗𝗲𝘃𝗗𝗮𝘆𝘀, 𝗗𝗲𝘃𝗢𝗽𝘀 𝗣𝗿𝗼, and 𝗖𝘆𝗯𝗲𝗿𝗪𝗶𝘀𝗲𝗖𝗼𝗻 𝗘𝘂𝗿𝗼𝗽𝗲 in Vilnius. A unique event bringing together developers, DevOps engineers, cybersecu..

devdays_devops_pro_cyberwisecon_europe_vilnius_2026_relianoid

Activity

@harshilmalvi started using tool Microsoft Power Platform , 1 month, 1 week ago.

vLLM is an advanced open-source framework for serving and running large language models efficiently at scale. Developed by researchers and engineers from UC Berkeley and adopted widely across the AI industry, vLLM focuses on optimizing inference performance through its innovative PagedAttention mechanism — a memory management system that enables near-zero waste in GPU memory utilization. It supports model parallelism, continuous batching, tensor parallelism, and dynamic batching across GPUs, making it ideal for real-world deployment of foundation models. vLLM integrates seamlessly with Hugging Face Transformers, OpenAI-compatible APIs, and popular orchestration tools like Ray Serve and Kubernetes. Its design allows developers and enterprises to host LLMs with reduced latency, lower hardware costs, and increased throughput, powering everything from chatbots to enterprise-scale AI services.