{
 "kind": "done",
 "sentence": "the phase ran to its end",
 "inner": {
  "t": 1790976681.169,
  "utc": "2026-10-02T21:31:21Z",
  "phase": "done",
  "runs": 9
 },
 "facts": {
  "arm": "L-IQ3",
  "phase": "speed",
  "attempt": 1,
  "arm_cfg": {
   "order": 1,
   "engine": "llama.cpp",
   "quant": "IQ3_S",
   "mtp": null,
   "contexts": [
    "4K",
    "32K",
    "128K"
   ],
   "quality": true,
   "pair": "S-IQ3",
   "band": [
    20,
    55
   ],
   "registered": true
  },
  "driver_started": "2026-10-02T20:53:21Z",
  "prereg": {
   "prereg_sha256": "withheld-2026-09-29",
   "recon_sha256": "96e4a739267cc85c250300d714faa51cc135f25ce69f61cb19fd6c286f826df0",
   "registered": "2026-10-02T19:26:17Z",
   "block_verbatim": true,
   "why": null
  },
  "files": {
   "1": {
    "path": "/data/strata-bench/models/ISTA-ed59f920/IQ3_S/Qwen3.8-Flash-Next-GSQ-RCO-IQ3_S-00001-of-00002.gguf",
    "pinned_sha256": "4c1eb2ceb4915e1192f4f386021897bde56a97f40a0bb78bb86465e0f7d2aca3",
    "receipt_sha256": "4c1eb2ceb4915e1192f4f386021897bde56a97f40a0bb78bb86465e0f7d2aca3",
    "receipt_at": "2026-10-02T20:08:17Z",
    "bytes": 54817524224,
    "mtime": "2026-10-02T20:07:50Z",
    "receipt_bytes_match": true,
    "ok": true
   },
   "2": {
    "path": "/data/strata-bench/models/ISTA-ed59f920/IQ3_S/Qwen3.8-Flash-Next-GSQ-RCO-IQ3_S-00002-of-00002.gguf",
    "pinned_sha256": "316b46f3a2dbd68c900f43136ab9449f9dcc3725dfd8c794847c204bc161e113",
    "receipt_sha256": "316b46f3a2dbd68c900f43136ab9449f9dcc3725dfd8c794847c204bc161e113",
    "receipt_at": "2026-10-02T20:06:46Z",
    "bytes": 28800138432,
    "mtime": "2026-10-02T20:06:33Z",
    "receipt_bytes_match": true,
    "ok": true
   }
  },
  "n_cpu_moe_frozen": {
   "arm": "L-IQ3",
   "n_cpu_moe": 34,
   "evidence": "L-IQ3/fit/a7/fit-001: max_used 22449 of 24463 MiB (2014 MiB left >= 1536); N=32 (a8) and N=30 (a9) failed to load (CUDA OOM)",
   "frozen": "2026-10-02T20:53:14Z"
  },
  "engine_commit": "3cf03257f219afbe7334045ff7c6a06ac68c627d",
  "server_argv": [
   "/data/strata-bench/build/llama.cpp-3cf03257/bin/llama-server",
   "-m",
   "/data/strata-bench/models/ISTA-ed59f920/IQ3_S/Qwen3.8-Flash-Next-GSQ-RCO-IQ3_S-00001-of-00002.gguf",
   "--host",
   "127.0.0.1",
   "--port",
   "withheld-2026-10-13",
   "-ngl",
   "99",
   "--n-cpu-moe",
   "34",
   "-c",
   "131072",
   "-fa",
   "on",
   "-ctk",
   "q8_0",
   "-ctv",
   "q8_0",
   "-lm",
   "mmap",
   "--lazy-mode",
   "on",
   "-fit",
   "off",
   "-np",
   "1",
   "--cache-ram",
   "0",
   "--no-webui",
   "--jinja",
   "-lv",
   "4"
  ],
  "memory_plan": {
   "memory_max_gib": 50,
   "need_gib": 40.2,
   "swap_max": "0",
   "arithmetic": "llama.cpp IQ3_S: CPU experts 34/48 x 46.84 GiB = 33.18 GiB of mmapped pages (--n-cpu-moe 34) + 3.0 GiB host buffers = 36.18 GiB working set; MemoryMax = min(working set + 14 GiB of page-cache room for the GPU layers' pages and the n-gram rows, MemTotal - 6) = 50 GiB (a page-cache reclaim at the cap shows as SSD reads/s, recorded per run, never as a kill); refuse below MemAvailable 40.2 GiB (working set + 4 GiB)."
  },
  "lock": {
   "path": "/workshop/CARD-LOCK",
   "sentence": "LOCK TAKEN: /workshop/CARD-LOCK now names strata-bench (token ffaeaf83ea49)"
  },
  "watcher": {
   "unit": "sb-watch-L-IQ3-speed-a1",
   "rc": 0,
   "argv": [
    "systemd-run",
    "--user",
    "--quiet",
    "--unit=sb-watch-L-IQ3-speed-a1",
    "--property=KillMode=control-group",
    "--property=TimeoutStopSec=30",
    "--working-directory=/workshop/bench-archive/plans-2026-10-02/strata-bench/harness",
    "--",
    "/usr/bin/python3",
    "/workshop/bench-archive/plans-2026-10-02/strata-bench/harness/restore_watcher.py",
    "--timer",
    "scribe-embed.timer",
    "--timer-stopped",
    "yes",
    "--engine-unit",
    "sb-eng-L-IQ3-speed-a1",
    "--lock",
    "/workshop/CARD-LOCK",
    "--lock-token",
    "ffaeaf83ea49",
    "--log",
    "/workshop/bench-archive/plans-2026-10-02/strata-bench/records/L-IQ3/speed/watcher-a1-2026-10-02T205324Z.log",
    "--deadline-s",
    "21600",
    "--systemctl",
    "systemctl --user",
    "--driver-unit",
    "sb-driver-L-IQ3-speed",
    "--done-file",
    "/workshop/bench-archive/plans-2026-10-02/strata-bench/records/L-IQ3/speed/watcher-a1.done"
   ],
   "log": "/workshop/bench-archive/plans-2026-10-02/strata-bench/records/L-IQ3/speed/watcher-a1-2026-10-02T205324Z.log"
  },
  "park": {
   "timer": {
    "timer": "scribe-embed.timer",
    "before": "active",
    "stopped_by_us": true,
    "stop_rc": 0,
    "stop_out": "",
    "after": "inactive"
   },
   "ollama": {
    "host_is_loopback": true,
    "ps_before": {
     "rc": 0,
     "text": "NAME    ID    SIZE    PROCESSOR    CONTEXT    UNTIL"
    },
    "loaded": [],
    "evicted": [],
    "loaded_after": [],
    "ps_after": {
     "rc": 0,
     "text": "NAME    ID    SIZE    PROCESSOR    CONTEXT    UNTIL"
    }
   }
  },
  "mem_available_after_park_gib": 52.466,
  "data_device": {
   "mount": "/data",
   "source": "/dev/nvme0n1p1",
   "partition": "nvme0n1p1",
   "disk": "nvme0n1",
   "model": "Samsung SSD 990 PRO 2TB",
   "hwmon_temp": "/sys/block/nvme0n1/device/hwmon3/temp1_input",
   "how": "findmnt -no SOURCE, then /sys/class/block/<part>'s parent and its hwmon"
  },
  "powercap": {
   "readable": false,
   "path": "/sys/class/powercap/intel-rapl:0/energy_uj",
   "why": "root-only (mode 0400) on this box: recorded null; /run/rapl/energy is read instead"
  },
  "psi_settle": {
   "waited_s": 0.0,
   "psi_start": 0.01,
   "psi_end": 0.01,
   "settled": true,
   "pct": 5.0,
   "max_s": 180.0
  },
  "vram_baseline_mib": 15.0,
  "unit": {
   "name": "sb-eng-L-IQ3-speed-a1",
   "argv": [
    "systemd-run",
    "--user",
    "--quiet",
    "--unit=sb-eng-L-IQ3-speed-a1",
    "--property=KillMode=control-group",
    "--property=TimeoutStopSec=30",
    "--property=MemoryMax=50G",
    "--property=MemorySwapMax=0",
    "--property=IPAddressDeny=any",
    "--property=IPAddressAllow=localhost",
    "--working-directory=/workshop/bench-archive/plans-2026-10-02/strata-bench/records/L-IQ3/speed/a1",
    "--property=StandardOutput=append:/workshop/bench-archive/plans-2026-10-02/strata-bench/records/L-IQ3/speed/a1/unit.log",
    "--property=StandardError=append:/workshop/bench-archive/plans-2026-10-02/strata-bench/records/L-IQ3/speed/a1/unit.log",
    "--setenv=PYTHONDONTWRITEBYTECODE=1",
    "--setenv=PYTHONUNBUFFERED=1",
    "--",
    "bwrap",
    "--unshare-net",
    "--unshare-pid",
    "--die-with-parent",
    "--ro-bind",
    "/",
    "/",
    "--dev-bind",
    "/dev",
    "/dev",
    "--proc",
    "/proc",
    "--tmpfs",
    "/run",
    "--tmpfs",
    "/tmp",
    "--bind",
    "/workshop/bench-archive/plans-2026-10-02/strata-bench/records",
    "/workshop/bench-archive/plans-2026-10-02/strata-bench/records",
    "--ro-bind",
    "/run/nvidia-persistenced",
    "/run/nvidia-persistenced",
    "--",
    "/usr/bin/python3",
    "/workshop/bench-archive/plans-2026-10-02/strata-bench/harness/inner.py",
    "--spec",
    "/workshop/bench-archive/plans-2026-10-02/strata-bench/records/L-IQ3/speed/a1/spec.json"
   ],
   "sandbox_notes": [
    "/var/run is a link to /run (or absent): the /run tmpfs covers it",
    "/run/nvidia-persistenced bound read-only (the driver's persistence socket)"
   ],
   "ip_filter": "IPAddressDeny=any + IPAddressAllow=localhost CONFIGURED; a user manager does not enforce them (it logs 'unit configures an IP firewall, but not running as root'); the enforced block is the sandbox, proved by the probe"
  },
  "egress_probe": {
   "ifaces_count": 1,
   "only_lo": true,
   "mode": "netns",
   "dns": "failed (gaierror)",
   "outside_connect": "failed (ENETUNREACH)",
   "loopback": "connected",
   "verdict": "enforced",
   "why": "only lo; DNS fails; a non-loopback connect fails; loopback answers"
  },
  "g0": {
   "verdict": "pass",
   "devices": {
    "cuda": 1,
    "vulkan": 0,
    "names": [
     "CUDA0"
    ],
    "rule": "src/llama.cpp L306 at b11081: one `using device` line per device the model is offloaded to"
   },
   "offload": {
    "verdict": "ok",
    "line": "offloaded 49/49 layers to GPU",
    "offloaded": 49,
    "of": 49,
    "sentence": "all 49 layers offloaded"
   },
   "why": "one CUDA device, no Vulkan; all 49 layers offloaded",
   "health": {
    "ready": true,
    "seconds": 19.03,
    "health": {
     "status": "ok"
    }
   }
  }
 },
 "unit_show_at_end": {
  "ActiveState": "active",
  "SubState": "running",
  "Result": "success",
  "NRestarts": "0",
  "ExecMainPID": "1793844",
  "ExecMainStatus": "0",
  "ControlGroup": "/user.slice/user-1000.slice/user@1000.service/app.slice/sb-eng-L-IQ3-speed-a1.service",
  "MemoryCurrent": "20975890432",
  "MemoryPeak": "25161502720",
  "MemoryMax": "53687091200",
  "MemorySwapMax": "0",
  "IPAddressAllow": "127.0.0.0/8 ::1/128",
  "IPAddressDeny": "0.0.0.0/0 ::/0"
 },
 "unit_memory_at_end": {
  "memory.current": "20975890432",
  "memory.peak": "25161502720",
  "memory.max": "53687091200",
  "memory.swap.current": "0",
  "memory.events": {
   "low": 0,
   "high": 0,
   "max": 0,
   "oom": 0,
   "oom_kill": 0,
   "oom_group_kill": 0,
   "sock_throttled": 30
  },
  "memory.stat": {
   "anon": 1146806272,
   "file": 19609800704,
   "kernel": 217772032,
   "shmem": 10485760,
   "file_mapped": 3195596800,
   "unevictable": 0
  }
 },
 "rows": 9,
 "rows_file": "rows.jsonl",
 "telemetry_file": "telemetry.csv",
 "uuid_scrubbed": {
  "server.log": 0,
  "unit.log": 0
 },
 "sampler_notes": [],
 "driver_ended": "2026-10-02T21:31:24Z",
 "marker": "RESULT",
 "arm": "L-IQ3",
 "phase": "speed",
 "attempt": 1,
 "written": "2026-10-02T21:31:24Z"
}