saved: 2026-10-30T17:20:57+01:00
B2003
7.0.0-38-generic
up 2 hours, 10 minutes
NVIDIA GeForce RTX 3060, 615.71.10, 170.00 W, 2160 MHz, 7501 MHz, 12288 MiB
gpu_unlock cmdline: gpu_unlock.targets=0000:02:00.0 
/home/user/Strata-data/engines-0.1.52
engine command lines (from serve log):
[strata] 2026-10-30 15:13:24 engine started: /home/user/Strata-data/engines-0.1.52/strata --serve --pack /home/user/Strata-data/packs/iq3_s --native /home/user/Strata-data/models/IQ3_S/Qwen3.8-Flash-Next-GSQ-RCO-IQ3_S-00001-of-00002.gguf --ple-gguf /home/user/Strata-data/models/IQ3_S/Qwen3.8-Flash-Next-GSQ-RCO-IQ3_S-00002-of-00002.gguf --expert-profile /home/user/Strata/repo/data/expert-profile.bin --expert-cache auto --prefill 4096 --spec 4 --spec-min-p 0.5 --mtp /home/user/Strata-data/mtp/rt --max-context 32768 --kv int8 --vision --vram-reserve-mib 960 --pool-workers 12 --kv-grow --conversation-cache-mib 1536 --conversation-cache-min-tokens 4096 --conversation-cache-park-gain 256 --prompt-cache-tail --prompt-cache-spread --conversation-cache-min-free-mib 1536 --resident-experts --resident-budget-gib 24 --kv-resident 32768
[strata] 2026-10-30 16:16:35 engine started: /home/user/Strata-data/engines-0.1.52/strata --serve --pack /home/user/Strata-data/packs/iq3_s --native /home/user/Strata-data/models/IQ3_S/Qwen3.8-Flash-Next-GSQ-RCO-IQ3_S-00001-of-00002.gguf --ple-gguf /home/user/Strata-data/models/IQ3_S/Qwen3.8-Flash-Next-GSQ-RCO-IQ3_S-00002-of-00002.gguf --expert-profile /home/user/Strata/repo/data/expert-profile.bin --expert-cache auto --prefill 4096 --spec 4 --spec-min-p 0.5 --mtp /home/user/Strata-data/mtp/rt --max-context 32768 --kv int8 --vision --vram-reserve-mib 960 --pool-workers 12 --kv-grow --conversation-cache-mib 1536 --conversation-cache-min-tokens 4096 --conversation-cache-park-gain 256 --prompt-cache-tail --prompt-cache-spread --conversation-cache-min-free-mib 1536 --resident-experts --resident-budget-gib 24 --kv-resident 32768
[strata] 2026-10-30 17:20:04 engine started: /home/user/Strata-data/engines-0.1.52/strata --serve --pack /home/user/Strata-data/packs/iq3_s --native /home/user/Strata-data/models/IQ3_S/Qwen3.8-Flash-Next-GSQ-RCO-IQ3_S-00001-of-00002.gguf --ple-gguf /home/user/Strata-data/models/IQ3_S/Qwen3.8-Flash-Next-GSQ-RCO-IQ3_S-00002-of-00002.gguf --expert-profile /home/user/Strata/repo/data/expert-profile.bin --expert-cache auto --prefill 4096 --spec 4 --spec-min-p 0.5 --mtp /home/user/Strata-data/mtp/rt --max-context 32768 --kv int8 --vision --vram-reserve-mib 960 --pool-workers 12 --kv-grow --conversation-cache-mib 1536 --conversation-cache-min-tokens 4096 --conversation-cache-park-gain 256 --prompt-cache-tail --prompt-cache-spread --conversation-cache-min-free-mib 1536 --resident-experts --resident-budget-gib 24 --kv-resident 32768
model files:
total 81657896
-rw-rw-r-- 1 user user 54817524224 Oct 12 18:12 Qwen3.8-Flash-Next-GSQ-RCO-IQ3_S-00001-of-00002.gguf
-rw-rw-r-- 1 user user          16 Oct 12 18:12 Qwen3.8-Flash-Next-GSQ-RCO-IQ3_S-00001-of-00002.gguf.done
-rw-rw-r-- 1 user user 28800138432 Oct 12 18:27 Qwen3.8-Flash-Next-GSQ-RCO-IQ3_S-00002-of-00002.gguf
-rw-rw-r-- 1 user user          16 Oct 12 18:27 Qwen3.8-Flash-Next-GSQ-RCO-IQ3_S-00002-of-00002.gguf.done
routing arms seen (guard log):
2026-10-30T11:26:05+01:00 start tag=A prior=
2026-10-30T11:29:31+01:00 start prior=1.5 avail=45223MiB
2026-10-30T11:49:15+01:00 start prior=0 avail=45235MiB
2026-10-30T14:07:33+01:00 start prior=0 avail=45173MiB
2026-10-30T16:16:33+01:00 start prior=0 avail=45216MiB
