{
 "schema": "local-ai-bench/result/v1",
 "run_id": "20261005T083536Z-sglang-qwen3.8-27b-exl3-3.00bpw-nextn-200k-rtx-3090-24gb-omarchy-gpu2-lab",
 "ticket": "T40",
 "kind": "lab",
 "model": "qwen3.8-27b",
 "config_id": "sglang-qwen3.8-27b-exl3-3.00bpw-nextn-200k-rtx-3090-24gb-omarchy-gpu2",
 "outcome": "fail",
 "failed_stage": "gates",
 "exit_status": 1,
 "started_at": "2026-10-05T08:35:36.632766+00:00",
 "finished_at": "2026-10-05T08:36:27.955819+00:00",
 "launch": {
  "file": "launches/sglang-qwen3.8-27b-exl3-3.00bpw-nextn-200k-rtx-3090-24gb-omarchy.json",
  "sha256": "c4b825a12a5c77c6e174f31bce8236f5a51644c6ec2b576ab3760ca54d6ee925",
  "image": "ghcr.io/0xsero/sglang-exl3@sha256:84f75f3424c99a3d63392a4e0348292bdeba9cf7efba2ff1aa9b85c8fc0131e8",
  "argv": [
   "/opt/entrypoint.sh",
   "python3",
   "-m",
   "sglang.launch_server",
   "--model-path",
   "/models/turboderp-Qwen3.8-27B-exl3-3.00bpw",
   "--quantization",
   "exl3",
   "--trust-remote-code",
   "--host",
   "0.0.0.0",
   "--port",
   "30000",
   "--served-model-name",
   "turboderp-Qwen3.8-27B-exl3-3.00bpw",
   "--context-length",
   "204800",
   "--mem-fraction-static",
   "0.80",
   "--kv-cache-dtype",
   "fp8_e4m3",
   "--mamba-ssm-dtype",
   "bfloat16",
   "--max-running-requests",
   "1",
   "--max-mamba-cache-size",
   "5",
   "--cuda-graph-max-bs-decode",
   "1",
   "--chunked-prefill-size",
   "1024",
   "--max-prefill-tokens",
   "1024",
   "--reasoning-parser",
   "qwen3",
   "--tool-call-parser",
   "qwen3_coder",
   "--speculative-algorithm",
   "NEXTN",
   "--speculative-num-steps",
   "3",
   "--speculative-eagle-topk",
   "1",
   "--speculative-num-draft-tokens",
   "4",
   "--speculative-token-map",
   "/opt/sglang-exl3/tokenmaps/qwen38_hot32k_v2.pt"
  ],
  "env": {
   "HF_HUB_OFFLINE": "1",
   "CUDA_DEVICE_ORDER": "PCI_BUS_ID"
  },
  "engine": "sglang-exl3",
  "engine_source_commit": null,
  "mtp": {
   "algorithm": "NEXTN",
   "num_steps": 3,
   "eagle_topk": 1,
   "draft_tokens": 4,
   "token_map": "qwen38_hot32k_v2.pt"
  },
  "entrypoint": "/opt/entrypoint.sh",
  "port": 30000,
  "shm": "16g",
  "flags": [],
  "weights_at": [
   "/models"
  ]
 },
 "weights": [
  {
   "repo": "turboderp/Qwen3.8-27B-exl3",
   "revision": "6fe61ad620abfe97c5b49f9722c2bceeea4ccc28",
   "manifest": "models/turboderp-Qwen3.8-27B-exl3-3.00bpw-src.json"
  }
 ],
 "host": {
  "hostname": "omarchy-gpu",
  "cpu": "AMD Ryzen 9 5950X 16-Core Processor",
  "ram_total_gib": 125.7,
  "ram_layout": "DIMM_A1 32 GiB DDR4 3200 MT/s, DIMM_A2 32 GiB DDR4 3200 MT/s, DIMM_B1 32 GiB DDR4 3200 MT/s, DIMM_B2 32 GiB DDR4 3200 MT/s (AM4: 2 channels)",
  "kernel": "7.2.5-3-omarchy",
  "driver": "610.57.04",
  "cuda": "13.3",
  "cpus_online": "0-1,3-17,19-31",
  "cpus_offline": "2,18",
  "cpu_boost": false,
  "cpu_max_mhz": 3401,
  "machine_checks_this_boot": 6
 },
 "gpus": [
  {
   "index": 0,
   "uuid": "GPU-816b43e4-8d65-dfd7-2234-8517b3dfbf2d",
   "name": "NVIDIA GeForce RTX 3090",
   "bus_id": "00000000:04:00.0",
   "pcie_gen_max": 4,
   "pcie_width": 8,
   "display_active": false,
   "used_by_run": false
  },
  {
   "index": 1,
   "uuid": "GPU-c67ac872-3371-a88c-aa92-d969daf6405e",
   "name": "NVIDIA GeForce RTX 3090",
   "bus_id": "00000000:0B:00.0",
   "pcie_gen_max": 4,
   "pcie_width": 8,
   "display_active": true,
   "used_by_run": false
  },
  {
   "index": 2,
   "uuid": "GPU-76d3c6af-7f18-69d2-3145-899103de1722",
   "name": "NVIDIA GeForce RTX 3090",
   "bus_id": "00000000:0C:00.0",
   "pcie_gen_max": 4,
   "pcie_width": 8,
   "display_active": false,
   "used_by_run": true
  }
 ],
 "layout": {
  "name": "current",
  "cards": 1,
  "display": "on"
 },
 "context": {
  "configured": 204800,
  "occupied_max": {
   "state": "unavailable",
   "reason": "no occupancy measured in this run"
  },
  "headroom_min": {
   "state": "unavailable",
   "reason": "no occupancy measured in this run"
  }
 },
 "cache_state": {
  "cold": false,
  "reset": []
 },
 "provenance": {
  "bench_commit": "7601cd0b9171268d7ab9b01200decc2680ca4987",
  "bench_dirty": true,
  "pins_sha256": "858564b6e07125ac48c2ef6c5178d0a53596f21eb5f0ebda43906472b01b4d78",
  "registry_commit": "d21258dd744e7c78be28177c90060c6af8e10b7e",
  "kit_commit": "ef883d269e50ecbea290f919f095e2f3ca633b42",
  "harness_commit": "04d809ceab9df28f9adaed044884180159172930"
 },
 "metrics": {
  "mtp_acceptance_rate": {
   "value": 0.71,
   "unit": "fraction",
   "detail": {
    "mean_accept_len": 3.123,
    "batches": 4,
    "source": "SGLang decode log"
   }
  },
  "mtp_accepted_tps": {
   "state": "unavailable",
   "reason": "no decode speed in this step"
  },
  "gates_passed": {
   "state": "unavailable",
   "reason": "not produced (fail/gates)"
  },
  "lab_decode_c1_tps": {
   "state": "unavailable",
   "reason": "not produced (fail/gates)"
  },
  "lab_prefill_tps": {
   "state": "unavailable",
   "reason": "not produced (fail/gates)"
  }
 },
 "eligibility": "none",
 "artifacts": [
  "artifacts/runs/20261005T083536Z-lab-sglang-qwen3.8-27b-exl3-3.00bpw-nextn-200k-rtx-3090-24gb-oma-lab"
 ],
 "notes": ""
}
