https://curadevops.metacog.co.kr/tags/llm/Recent content in Llm on CuraDevOpsHugoen-usSat, 25 Jul 2026 11:58:38 +0000https://curadevops.metacog.co.kr/insights/2026-07-25-claude-opus-5-is-now-available-in-github-copilot/Sat, 25 Jul 2026 11:58:38 +0000https://curadevops.metacog.co.kr/insights/2026-07-25-claude-opus-5-is-now-available-in-github-copilot/<ul> <li><strong>Platform/SRE — Skip</strong></li> <li><strong>CI/CD — Skip</strong></li> <li><strong>Leader — Learn:</strong> A more capable reasoning model is now available in GitHub Copilot; relevant if the org is evaluating AI coding assistant ROI or comparing Copilot seat value against alternatives.</li> </ul>https://curadevops.metacog.co.kr/insights/2026-07-20-why-goodput-matters-more-than-throughput-for-llm-serving/Mon, 20 Jul 2026 13:01:38 +0000https://curadevops.metacog.co.kr/insights/2026-07-20-why-goodput-matters-more-than-throughput-for-llm-serving/<ul> <li><strong>Platform/SRE — Learn:</strong> Reframes how to evaluate LLM inference infrastructure capacity; useful context when sizing or optimizing a self-hosted model-serving stack, but no operational change required today.</li> <li><strong>CI/CD — Skip</strong></li> <li><strong>Leader — Skip</strong></li> </ul>https://curadevops.metacog.co.kr/insights/2026-07-16-running-a-self-hosted-llm-in-kubernetes-with-vllm/Thu, 16 Jul 2026 12:15:50 +0000https://curadevops.metacog.co.kr/insights/2026-07-16-running-a-self-hosted-llm-in-kubernetes-with-vllm/<ul> <li><strong>Platform/SRE — Learn:</strong> Useful reference for platform engineers evaluating GPU workload patterns on Kubernetes; no forced migration or deadline, but shapes how you&rsquo;d design node pools and scheduling for LLM inference.</li> <li><strong>CI/CD — Skip</strong></li> <li><strong>Leader — Learn:</strong> Relevant context for build-vs-buy decisions on LLM inference — self-hosting via vLLM vs managed API services — but no concrete strategic decision is forced by this content.</li> </ul>