diff --git a/script/infra-setup.sh b/script/infra-setup.sh index 5655ae3..0f60def 100755 --- a/script/infra-setup.sh +++ b/script/infra-setup.sh @@ -67,9 +67,11 @@ GPU_POWER_LIMITS="${GPU_POWER_LIMITS-beast.hanzalova.internal=300 benjy.hanzalov # SMs inside the same power cap: locking it at 810 MHz measured +13% on the # 4090 at 250 W (410 -> 463 MH/s) and +2% on the 3060 at 130 W. 405 MHz drops # the card into a low-power state and must not be used. Hosts serving -# inference (beast) are NOT listed: LLM inference is memory-bound. A host with -# no entry gets its memory clock reset to the driver default. -GPU_MEMORY_CLOCKS="${GPU_MEMORY_CLOCKS-benjy.hanzalova.internal=810 quadbrat.hanzalova.internal=810}" +# beast joined 2026-09-09 once inference was switched off there (+2% on each +# 5090 at 400 W, 555 -> 567 MH/s, SM clock 2250 -> 2370 MHz); a host serving +# LLM inference must NOT be listed, inference is memory-bound. A host with no +# entry gets its memory clock reset to the driver default. +GPU_MEMORY_CLOCKS="${GPU_MEMORY_CLOCKS-benjy.hanzalova.internal=810 quadbrat.hanzalova.internal=810 beast.hanzalova.internal=810}" # Vanity name served by the edge proxy. Dot-free short name: the step@ renewal # unit is a template instance and %i cannot carry dots (internal-tls.md ยง1). EDGE_NAME="${EDGE_NAME:-quantus}"