[{"id":"IL-0480","title":{"en":"Epoch-end NCCL deadlock hung a 16-GPU B300 fine-tuning run for three hours while GPU utilization read 100%","ko":"B300 16장 FSDP 미세 조정이 에포크 끝 체크포인트에서 NCCL 교착으로 세 시간 동안 조용히 멈췄다"},"org":"Samsung SDS","org_slug":"samsung-sds","date":"2026-08-06","severity":"unknown","root_cause":"software-bug","url":"https://benchlet.com/incidentlib/app/cases/IL-0480","shared_components":["nccl"]},{"id":"IL-0344","title":{"en":"Linode's US-West data centers in Fremont and Santa Clara lost connectivity as the fibre circuits between them failed","ko":"Linode US-West 의 Fremont 와 Santa Clara 데이터 센터가 인터넷 연결과 두 사이트 사이 연결을 잃었다"},"org":"Linode","org_slug":"linode","date":"2023-02-11","severity":"unknown","root_cause":"software-bug","url":"https://benchlet.com/incidentlib/app/cases/IL-0344","shared_components":["network-link"]},{"id":"IL-0263","title":{"en":"GitHub was slow and erroring all day and down for 18 minutes as links between access and aggregation switches saturated","ko":"새 애그리게이션 스위치로 옮기는 작업 뒤 데이터센터 스위치 사이 링크가 포화되어 GitHub 가 하루 종일 느렸고 18분 동안 완전히 멈췄다"},"org":"GitHub","org_slug":"github","date":"2012-11-30","severity":"unknown","root_cause":"software-bug","url":"https://benchlet.com/incidentlib/app/cases/IL-0263","shared_components":["network-link"]}]