present: Maria, David, Matt, CP
Report of the week 34:
- login nodes better behaving: not saturated by users, so the modifications from David were useful
David:
- updated Alarms of the certificate expiring (David)
- ceph - latest fix vulnerability (David)
- needed update various keys (took ~ 1 day)
- alarms updated
- cleanup of various partitions
Matt:
Maria:
- minor improvements in the user/admin guide
Long term:
- more modern GPU welcome: i.e. to host more complex model on ollama/VLLM resources
from Jason/Archi: "I got qwen 3.8 27b running on submit76. With all four v100s it's roughly 50 tok/s decode, 500/s prefill for a single request. Parallel requests it's about 100 tok/s decode, 1000/s prefill. Does submit have any other GPUs that are more modern? the tough thing with v100s is many kernels aren't supported "