| 123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475767778798081828384 |
- {"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 0:02:11
- llama-benchy 0.4.0
- Estimated latency: 73.8 ms
- llama-benchy Results
- ┏━━━━━━━━━━━━━━━━━━━━━━┳━━━━┳━━━━━━━━━┳━━━━━━━━━┳━━━━━━━━━━┳━━━━━━━━━━┳━━━━━━━━━
- ┃ ┃ ┃ ┃ ┃ TTFT ┃ Total ┃
- ┃ Test ┃ c ┃ pp t/s ┃ tg t/s ┃ (ms) ┃ (ms) ┃ Tokens
- ┡━━━━━━━━━━━━━━━━━━━━━━╇━━━━╇━━━━━━━━━╇━━━━━━━━━╇━━━━━━━━━━╇━━━━━━━━━━╇━━━━━━━━━
- │ pp2048 tg128 @ d0 │ c1 │ 1,900 │ 47.7 │ 1,026 │ 3,634 │ 2048+128
- │ pp2048 tg128 @ d0 │ c2 │ 1,716 │ 58.9 │ 1,567 │ 5,181 │ 2048+128
- │ pp2048 tg128 @ d4096 │ c1 │ 1,910 │ 44.6 │ 2,899 │ 5,692 │ 2048+128
- │ pp2048 tg128 @ d4096 │ c2 │ 1,950 │ 56.3 │ 5,100 │ 8,949 │ 2048+128
- │ pp2048 tg128 @ d8192 │ c1 │ 2,000 │ 47.7 │ 4,602 │ 7,211 │ 2048+128
- │ pp2048 tg128 @ d8192 │ c2 │ 1,954 │ 52.6 │ 8,536 │ 12,208 │ 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": 4.72}
- {"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": 3.89}
- {"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": 5.8}
- {"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": 2.25}
- {"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": 11.55}
- {"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": 4.01}
- {"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": 11.13}
- {"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": 8.43}
- {"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": 5.19}
- {"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": 1.93}
- {"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": 1.91}
- {"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": 9.74}
- {"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": 7.27}
- {"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": 6.02}
- {"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": 4.82}
- {"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": 5.25}
- {"event": "scenario_start", "scenario_id": "TC-17", "title": "Timezone-Aware Scheduling", "category": "F", "index": 16, "total": 88}
- {"event": "scenario_result", "scenario_id": "TC-17", "status": "pass", "points": 2, "index": 16, "total": 88, "duration_seconds": 5.8}
- {"event": "scenario_start", "scenario_id": "TC-18", "title": "Translate & Forward", "category": "F", "index": 17, "total": 88}
- {"event": "scenario_result", "scenario_id": "TC-18", "status": "pass", "points": 2, "index": 17, "total": 88, "duration_seconds": 8.51}
- {"event": "scenario_start", "scenario_id": "TC-19", "title": "Message Routing", "category": "G", "index": 18, "total": 88}
- {"event": "scenario_result", "scenario_id": "TC-19", "status": "pass", "points": 2, "index": 18, "total": 88, "duration_seconds": 4.78}
- {"event": "scenario_start", "scenario_id": "TC-20", "title": "Data Extraction & Calculation", "category": "G", "index": 19, "total": 88}
- {"event": "scenario_result", "scenario_id": "TC-20", "status": "pass", "points": 2, "index": 19, "total": 88, "duration_seconds": 10.57}
- {"event": "scenario_start", "scenario_id": "TC-21", "title": "Constraint Validation", "category": "G", "index": 20, "total": 88}
- {"event": "scenario_result", "scenario_id": "TC-21", "status": "pass", "points": 2, "index": 20, "total": 88, "duration_seconds": 20.96}
- {"event": "scenario_start", "scenario_id": "TC-22", "title": "Output Format Compliance", "category": "H", "index": 21, "total": 88}
- {"event": "scenario_result", "scenario_id": "TC-22", "status": "pass", "points": 2, "index": 21, "total": 88, "duration_seconds": 1.64}
- {"event": "scenario_start", "scenario_id": "TC-23", "title": "Explicit Tool Prohibition", "category": "H", "index": 22, "total": 88}
- {"event": "scenario_result", "scenario_id": "TC-23", "status": "pass", "points": 2, "index": 22, "total": 88, "duration_seconds": 12.04}
- {"event": "scenario_start", "scenario_id": "TC-24", "title": "Multi-Constraint Instruction", "category": "H", "index": 23, "total": 88}
- {"event": "scenario_result", "scenario_id": "TC-24", "status": "pass", "points": 2, "index": 23, "total": 88, "duration_seconds": 2.03}
- {"event": "scenario_start", "scenario_id": "TC-25", "title": "Cross-Reference Prior Results", "category": "I", "index": 24, "total": 88}
- {"event": "scenario_result", "scenario_id": "TC-25", "status": "pass", "points": 2, "index": 24, "total": 88, "duration_seconds": 11.39}
- {"event": "scenario_start", "scenario_id": "TC-26", "title": "State Consistency (Multi-Turn)", "category": "I", "index": 25, "total": 88}
- {"event": "scenario_result", "scenario_id": "TC-26", "status": "pass", "points": 2, "index": 25, "total": 88, "duration_seconds": 7.4}
- {"event": "scenario_start", "scenario_id": "TC-27", "title": "Deduplication Awareness", "category": "I", "index": 26, "total": 88}
- {"event": "scenario_result", "scenario_id": "TC-27", "status": "pass", "points": 2, "index": 26, "total": 88, "duration_seconds": 5.7}
- {"event": "scenario_start", "scenario_id": "TC-28", "title": "Read-Before-Write", "category": "J", "index": 27, "total": 88}
|