row w2-r-s139-iq3 (R-S139-IQ3, ROW_KIND=strata) · started 2026-10-07T07:38:15Z · uid 1000 · python 3.14.4 CUDA_DEVICE_ORDER=PCI_BUS_ID CUDA_VISIBLE_DEVICES=0 TZ=UTC pins: 52 files read their sha256 again in 2.1 s (the 2 shards were read at the window's open) identity before the launch: the client's nine prompt digests equal L-IQ3-t8's (9/9) port withheld-2026-10-13 reads free on the box (ss -ltn) the Strata tree: HEAD 6f32ec070f23ced9f50e704d854d775da52591ab and `git status --porcelain --ignored` empty the engine's build identity: the build tree names the source tree, whose HEAD is the arm's commit (/workshop/bench-flashnext/build/strata-6f32ec07/CMakeCache.txt) the engine line (the laptop's, pinned): --pack /workshop/bench-flashnext/packs-6f32ec07/iq3_s --native /workshop/bench-flashnext/models/IQ3_S/Qwen3.8-Flash-Next-GSQ-RCO-IQ3_S-00001-of-00002.gguf --ple-gguf /workshop/bench-flashnext/models/IQ3_S/Qwen3.8-Flash-Next-GSQ-RCO-IQ3_S-00002-of-00002.gguf --expert-profile /workshop/bench-flashnext/strata-6f32ec07/data/expert-profile.bin --expert-cache auto --prefill auto --spec 4 --spec-min-p 0.5 --mtp /workshop/bench-flashnext/mtp/rt-6f32ec07 --max-context 131072 --kv int8 setup's rule for this box's MemTotal (123.39 GiB) would write: --pack /workshop/bench-flashnext/packs-6f32ec07/iq3_s --native /workshop/bench-flashnext/models/IQ3_S/Qwen3.8-Flash-Next-GSQ-RCO-IQ3_S-00001-of-00002.gguf --ple-gguf /workshop/bench-flashnext/models/IQ3_S/Qwen3.8-Flash-Next-GSQ-RCO-IQ3_S-00002-of-00002.gguf --expert-profile /workshop/bench-flashnext/strata-6f32ec07/data/expert-profile.bin --expert-cache auto --prefill auto --spec 4 --spec-min-p 0.5 --mtp /workshop/bench-flashnext/mtp/rt-6f32ec07 --max-context 131072 --kv int8 --kv-resident 32768 [NOT USED] engine env {'STRATA_NO_LARGEPAGES': '1'} (the client's allowlist passed); THP 'enabled=madvise defrag=madvise' as staged server argv: /usr/bin/python3 /workshop/bench-flashnext/strata-6f32ec07/serve/server.py --engine strata --config /workshop/desktop-window-2/row/R-S139-IQ3.run/strata-config.json --port withheld-2026-10-13 the second fence (the unit's IP rules), inner.py's ipfilter probe: enforced (a connect to the box's own non-loopback address is dropped (the IP filter is enforced); loopback answers) sandbox: /usr/bin/bwrap --unshare-net --unshare-pid --die-with-parent --ro-bind / / --dev-bind /dev /dev --proc /proc --tmpfs /run --tmpfs /tmp --bind /workshop/desktop-window-2/row/R-S139-IQ3.run /workshop/desktop-window-2/row/R-S139-IQ3.run --ro-bind /run/nvidia-persistenced /run/nvidia-persistenced -- /usr/bin/python3 /workshop/desktop-window-2/client/inner.py --spec /workshop/desktop-window-2/row/R-S139-IQ3.run/spec.json sandbox note: /var/run is a link to /run (or absent): the /run tmpfs covers it sandbox note: /run/nvidia-persistenced bound read-only (the driver's persistence socket) cards before: index, pci.bus_id, name, memory.used [MiB], memory.total [MiB], enforced.power.limit [W], temperature.gpu 0, withheld-2026-10-13, NVIDIA RTX PRO 6000 Blackwell Workstation Edition, 2 MiB, 97887 MiB, 300.00 W, 34 1, withheld-2026-10-13, NVIDIA GeForce RTX 3090 Ti, 18099 MiB, 24564 MiB, 350.00 W, 39 the pinned card's memory.used before the launch: 2.0 MiB residency at ready: partial residency (24576 of 24,576 slots; hit rate unread) (failed: no hit-rate line on any finished request (zero-doorbell: lookups 0); no PCIe share on any finished request (absent or 0)) server maps: /workshop/bench-flashnext/build/strata-6f32ec07/strata, /workshop/bench-flashnext/cuda-13.4/targets/x86_64-linux/lib/libcublas.so.13.8.0.4, /workshop/bench-flashnext/cuda-13.4/targets/x86_64-linux/lib/libcublasLt.so.13.8.0.4, /workshop/bench-flashnext/cuda-13.4/targets/x86_64-linux/lib/libcudart.so.13.4.92, /usr/lib/x86_64-linux-gnu/libcuda.so.595.84 cards after: index, pci.bus_id, name, memory.used [MiB], memory.total [MiB], enforced.power.limit [W], temperature.gpu 0, withheld-2026-10-13, NVIDIA RTX PRO 6000 Blackwell Workstation Edition, 2 MiB, 97887 MiB, 300.00 W, 53 1, withheld-2026-10-13, NVIDIA GeForce RTX 3090 Ti, 18099 MiB, 24564 MiB, 350.00 W, 40 residency at the end: whole ended 2026-10-07T07:41:05Z · inner rc 0 · last phase done · identity 9/9 · residency whole · fences held ['netns', 'unit_ip_filter']