123 lines
4.0 KiB
JSON
123 lines
4.0 KiB
JSON
{
|
|
"evidence_class": "local-real",
|
|
"host": {
|
|
"accelerator_name": "Radeon 8060S Graphics",
|
|
"accelerator_runtime": "7.13.26183",
|
|
"benchmark_lane": "cpu-controlled-baseline",
|
|
"converter_sha256": "c819f18fb22927b49fabc3b35d1c9e21ee638b3817eccd1bd4efbcc7116eeb4d",
|
|
"cpu_count": 32,
|
|
"cuda_available": true,
|
|
"hostname": "fedora",
|
|
"llama_cpp_commit": "e920c523e3b8a0163fe498af5bf90df35ff51d25",
|
|
"llama_cpp_version": "9991",
|
|
"llama_server_sha256": "fd8fe612970f23e447f2e717cfa51665be06b8d7315ba60556e010f6bca510dd",
|
|
"platform": "Linux-7.0.14-101.fc43.x86_64-x86_64-with-glibc2.42",
|
|
"python": "3.12.13",
|
|
"quantizer_sha256": "bd0cc8c7be6d48aad4755b31062e0e59a887cbadd43dbb8771853d5858bb198f",
|
|
"torch_version": "2.10.0+rocm7.13.0a20260513",
|
|
"transformers_version": "5.13.0"
|
|
},
|
|
"model_id": "Qwen/Qwen2.5-0.5B-Instruct",
|
|
"model_revision": "7ae557604adf67be50417f59c2c2f167def9a775",
|
|
"plan_sha256": "efe24690a9a7164bac6ab3fd0a6b22f078fc08aaefcfb96210ddf154e6050570",
|
|
"recipes": {
|
|
"llama-cpp-near-lossless-quality": {
|
|
"artifact_bytes": 994156448,
|
|
"available": true,
|
|
"concurrency": {
|
|
"1": {
|
|
"aggregate_decode_tokens_per_sec": 73.7861,
|
|
"decode_tokens_per_sec": 87.9728,
|
|
"failures": 0,
|
|
"latency_p50_ms": 385.2049,
|
|
"latency_p95_ms": 560.2939,
|
|
"peak_rss_bytes": 1110708224,
|
|
"peak_vram_bytes": 0,
|
|
"prefill_tokens_per_sec": 1427.2072,
|
|
"ttft_p50_ms": 43.929,
|
|
"ttft_p95_ms": 107.003
|
|
},
|
|
"4": {
|
|
"aggregate_decode_tokens_per_sec": 211.3515,
|
|
"decode_tokens_per_sec": 73.8932,
|
|
"failures": 0,
|
|
"latency_p50_ms": 467.5094,
|
|
"latency_p95_ms": 790.862,
|
|
"peak_rss_bytes": 1129578496,
|
|
"peak_vram_bytes": 0,
|
|
"prefill_tokens_per_sec": 1077.8162,
|
|
"ttft_p50_ms": 33.612,
|
|
"ttft_p95_ms": 128.501
|
|
}
|
|
},
|
|
"device": "cpu",
|
|
"lane": "quality"
|
|
},
|
|
"llama-cpp-quantized-performance-fit": {
|
|
"artifact_bytes": 397807520,
|
|
"available": true,
|
|
"concurrency": {
|
|
"1": {
|
|
"aggregate_decode_tokens_per_sec": 110.0458,
|
|
"decode_tokens_per_sec": 170.131,
|
|
"failures": 0,
|
|
"latency_p50_ms": 258.0681,
|
|
"latency_p95_ms": 465.8523,
|
|
"peak_rss_bytes": 542167040,
|
|
"peak_vram_bytes": 0,
|
|
"prefill_tokens_per_sec": 783.3775,
|
|
"ttft_p50_ms": 23.847,
|
|
"ttft_p95_ms": 237.696
|
|
},
|
|
"4": {
|
|
"aggregate_decode_tokens_per_sec": 206.377,
|
|
"decode_tokens_per_sec": 83.543,
|
|
"failures": 0,
|
|
"latency_p50_ms": 413.3897,
|
|
"latency_p95_ms": 910.253,
|
|
"peak_rss_bytes": 572788736,
|
|
"peak_vram_bytes": 0,
|
|
"prefill_tokens_per_sec": 474.3116,
|
|
"ttft_p50_ms": 67.945,
|
|
"ttft_p95_ms": 431.804
|
|
}
|
|
},
|
|
"device": "cpu",
|
|
"lane": "performance-fit"
|
|
},
|
|
"transformers-safetensors-reference": {
|
|
"artifact_bytes": 999586347,
|
|
"available": true,
|
|
"concurrency": {
|
|
"1": {
|
|
"aggregate_decode_tokens_per_sec": 40.3425,
|
|
"decode_tokens_per_sec": 46.1451,
|
|
"failures": 0,
|
|
"latency_p50_ms": 795.4807,
|
|
"latency_p95_ms": 930.9725,
|
|
"peak_rss_bytes": 1941213184,
|
|
"peak_vram_bytes": 0,
|
|
"prefill_tokens_per_sec": 671.8016,
|
|
"ttft_p50_ms": 37.4548,
|
|
"ttft_p95_ms": 193.4633
|
|
},
|
|
"4": {
|
|
"aggregate_decode_tokens_per_sec": 47.0903,
|
|
"decode_tokens_per_sec": 13.1337,
|
|
"failures": 0,
|
|
"latency_p50_ms": 2631.0031,
|
|
"latency_p95_ms": 3073.7389,
|
|
"peak_rss_bytes": 2177265664,
|
|
"peak_vram_bytes": 0,
|
|
"prefill_tokens_per_sec": 247.5617,
|
|
"ttft_p50_ms": 94.3995,
|
|
"ttft_p95_ms": 444.6749
|
|
}
|
|
},
|
|
"device": "cpu",
|
|
"lane": "quality"
|
|
}
|
|
},
|
|
"reference_recipe_id": "transformers-safetensors-reference"
|
|
}
|