{"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 0:03:05

  llama-benchy 0.4.0
  Estimated latency: 82.4 ms

                               llama-benchy Results                             
┏━━━━━━━━━━━━━━━━━━━━━━┳━━━━┳━━━━━━━━━┳━━━━━━━━━┳━━━━━━━━━━┳━━━━━━━━━━┳━━━━━━━━━
┃                      ┃    ┃         ┃         ┃     TTFT ┃    Total ┃         
┃ Test                 ┃ c  ┃  pp t/s ┃  tg t/s ┃     (ms) ┃     (ms) ┃   Tokens
┡━━━━━━━━━━━━━━━━━━━━━━╇━━━━╇━━━━━━━━━╇━━━━━━━━━╇━━━━━━━━━━╇━━━━━━━━━━╇━━━━━━━━━
│ pp2048 tg128 @ d0    │ c1 │   1,567 │    29.1 │    1,272 │    5,588 │ 2048+128
│ pp2048 tg128 @ d0    │ c2 │   1,449 │    36.2 │    1,871 │    8,000 │ 2048+128
│ pp2048 tg128 @ d4096 │ c1 │   1,670 │    25.6 │    3,265 │    8,190 │ 2048+128
│ pp2048 tg128 @ d4096 │ c2 │   1,654 │    34.5 │    5,928 │   12,305 │ 2048+128
│ pp2048 tg128 @ d8192 │ c1 │   1,701 │    25.7 │    5,452 │   10,342 │ 2048+128
│ pp2048 tg128 @ d8192 │ c2 │   1,682 │    32.5 │    9,735 │   16,066 │ 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": 6.99}
{"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": 6.3}
{"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": 11.98}
{"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": 3.44}
{"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": 19.18}
{"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": 6.46}
{"event": "scenario_start", "scenario_id": "TC-07", "title": "Search \u2192 Read \u2192 Act", "category": "C", "index": 6, "total": 88}
{"event": "scenario_result", "scenario_id": "TC-07", "status": "pass", "points": 2, "index": 6, "total": 88, "duration_seconds": 19.2}
{"event": "scenario_start", "scenario_id": "TC-08", "title": "Conditional Branching", "category": "C", "index": 7, "total": 88}
{"event": "scenario_result", "scenario_id": "TC-08", "status": "pass", "points": 2, "index": 7, "total": 88, "duration_seconds": 13.21}
{"event": "scenario_start", "scenario_id": "TC-09", "title": "Parallel Independence", "category": "C", "index": 8, "total": 88}
{"event": "scenario_result", "scenario_id": "TC-09", "status": "pass", "points": 2, "index": 8, "total": 88, "duration_seconds": 9.4}
{"event": "scenario_start", "scenario_id": "TC-10", "title": "Trivial Knowledge", "category": "D", "index": 9, "total": 88}
{"event": "scenario_result", "scenario_id": "TC-10", "status": "pass", "points": 2, "index": 9, "total": 88, "duration_seconds": 3.95}
{"event": "scenario_start", "scenario_id": "TC-11", "title": "Simple Math", "category": "D", "index": 10, "total": 88}
{"event": "scenario_result", "scenario_id": "TC-11", "status": "pass", "points": 2, "index": 10, "total": 88, "duration_seconds": 3.02}
{"event": "scenario_start", "scenario_id": "TC-12", "title": "Impossible Request", "category": "D", "index": 11, "total": 88}
{"event": "scenario_result", "scenario_id": "TC-12", "status": "pass", "points": 2, "index": 11, "total": 88, "duration_seconds": 17.88}
{"event": "scenario_start", "scenario_id": "TC-13", "title": "Empty Results", "category": "E", "index": 12, "total": 88}
{"event": "scenario_result", "scenario_id": "TC-13", "status": "pass", "points": 2, "index": 12, "total": 88, "duration_seconds": 13.56}
{"event": "scenario_start", "scenario_id": "TC-14", "title": "Malformed Response", "category": "E", "index": 13, "total": 88}
{"event": "scenario_result", "scenario_id": "TC-14", "status": "pass", "points": 2, "index": 13, "total": 88, "duration_seconds": 10.91}
{"event": "scenario_start", "scenario_id": "TC-15", "title": "Conflicting Information", "category": "E", "index": 14, "total": 88}
{"event": "scenario_result", "scenario_id": "TC-15", "status": "pass", "points": 2, "index": 14, "total": 88, "duration_seconds": 8.49}
{"event": "scenario_start", "scenario_id": "TC-16", "title": "German Language Tool Call", "category": "F", "index": 15, "total": 88}
{"event": "scenario_result", "scenario_id": "TC-16", "status": "pass", "points": 2, "index": 15, "total": 88, "duration_seconds": 10.15}
{"event": "scenario_start", "scenario_id": "TC-17", "title": "Timezone-Aware Scheduling", "category": "F", "index": 16, "total": 88}