^D{"event": "backend_detected", "backend": "vllm"}

╭──────────────────── ⚡ llama-benchy Throughput Benchmark ────────────────────╮
│ glm53                                                                        │
│ pp=[2048]  tg=[128]  depth=[0, 4096, 8192]  concurrency=[1, 2]  runs=3       │
│ latency=generation                                                           │
╰──────────────────────────────────────────────────────────────────────────────╯

  ✓ Complete ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 18/18 0:03:46

  llama-benchy 0.4.0
  Estimated latency: 383.3 ms

                               llama-benchy Results                             
┏━━━━━━━━━━━━━━━━━━━━━━┳━━━━┳━━━━━━━━━┳━━━━━━━━━┳━━━━━━━━━━┳━━━━━━━━━━┳━━━━━━━━━
┃                      ┃    ┃         ┃         ┃     TTFT ┃    Total ┃         
┃ Test                 ┃ c  ┃  pp t/s ┃  tg t/s ┃     (ms) ┃     (ms) ┃   Tokens
┡━━━━━━━━━━━━━━━━━━━━━━╇━━━━╇━━━━━━━━━╇━━━━━━━━━╇━━━━━━━━━━╇━━━━━━━━━━╇━━━━━━━━━
│ pp2048 tg128 @ d0    │ c1 │   1,190 │    26.4 │    2,072 │    6,537 │ 2048+128
│ pp2048 tg128 @ d0    │ c2 │   1,317 │    33.5 │    2,717 │    9,686 │ 2048+128
│ pp2048 tg128 @ d4096 │ c1 │   1,366 │    27.8 │    4,354 │    8,581 │ 2048+128
│ pp2048 tg128 @ d4096 │ c2 │   1,321 │    29.8 │    7,481 │   14,648 │ 2048+128
│ pp2048 tg128 @ d8192 │ c1 │   1,371 │    27.9 │    6,952 │   11,155 │ 2048+128
│ pp2048 tg128 @ d8192 │ c2 │   1,373 │    28.1 │   12,349 │   19,937 │ 2048+128
└──────────────────────┴────┴─────────┴─────────┴──────────┴──────────┴─────────

  ℹ Metrics sourced from llama-benchy — see https://github.com/eugr/llama-benchy
for methodology.

{"event": "scenario_start", "scenario_id": "TC-01", "title": "Direct Specialist Match", "category": "A", "index": 0, "total": 88}
{"event": "scenario_result", "scenario_id": "TC-01", "status": "pass", "points": 2, "index": 0, "total": 88, "duration_seconds": 7.61}
{"event": "scenario_start", "scenario_id": "TC-02", "title": "Distractor Resistance", "category": "A", "index": 1, "total": 88}
{"event": "scenario_result", "scenario_id": "TC-02", "status": "pass", "points": 2, "index": 1, "total": 88, "duration_seconds": 7.27}
{"event": "scenario_start", "scenario_id": "TC-03", "title": "Implicit Tool Need", "category": "A", "index": 2, "total": 88}
{"event": "scenario_result", "scenario_id": "TC-03", "status": "pass", "points": 2, "index": 2, "total": 88, "duration_seconds": 13.54}
{"event": "scenario_start", "scenario_id": "TC-04", "title": "Unit Handling", "category": "B", "index": 3, "total": 88}
{"event": "scenario_result", "scenario_id": "TC-04", "status": "pass", "points": 2, "index": 3, "total": 88, "duration_seconds": 3.66}
{"event": "scenario_start", "scenario_id": "TC-05", "title": "Date and Time Parsing", "category": "B", "index": 4, "total": 88}
{"event": "scenario_result", "scenario_id": "TC-05", "status": "pass", "points": 2, "index": 4, "total": 88, "duration_seconds": 19.87}
{"event": "scenario_start", "scenario_id": "TC-06", "title": "Multi-Value Extraction", "category": "B", "index": 5, "total": 88}
{"event": "scenario_result", "scenario_id": "TC-06", "status": "pass", "points": 2, "index": 5, "total": 88, "duration_seconds": 7.21}
{"event": "scenario_start", "scenario_id": "TC-07", "title": "Search \u2192 Read \u2192 Act", "category": "C", "index": 6, "total": 88}