- PRD v1.0 plus addendum with environment reality checks (qwen3.5:9b pool, runaway protection, MVP trim) - Pre-implementation checklist and GitHub integration plan - ADR-001: build on Hermes Agent 0.19.0 as agent runtime; engine stays source of truth - ADR-002: engine stack (FastAPI, Postgres, Redis, React) - Benchmark suites + results: all five capability gates PASS, pool scaling 1.92x at 4 concurrent Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
264 lines
5.5 KiB
JSON
264 lines
5.5 KiB
JSON
{
|
|
"host": "http://192.168.1.5:4000",
|
|
"model": "qwen3.5:9b",
|
|
"warm": [
|
|
{
|
|
"wall_s": 5.81,
|
|
"load_s": 0.43,
|
|
"prompt_tokens": 24,
|
|
"prompt_eval_s": 0.25,
|
|
"gen_tokens": 256,
|
|
"gen_s": 5.06,
|
|
"tok_per_s": 50.6
|
|
},
|
|
{
|
|
"wall_s": 5.94,
|
|
"load_s": 0.43,
|
|
"prompt_tokens": 24,
|
|
"prompt_eval_s": 0.36,
|
|
"gen_tokens": 256,
|
|
"gen_s": 5.05,
|
|
"tok_per_s": 50.7
|
|
},
|
|
{
|
|
"wall_s": 7.45,
|
|
"load_s": 0.31,
|
|
"prompt_tokens": 24,
|
|
"prompt_eval_s": 0.19,
|
|
"gen_tokens": 256,
|
|
"gen_s": 6.78,
|
|
"tok_per_s": 37.7
|
|
}
|
|
],
|
|
"concurrency": {
|
|
"1": {
|
|
"wall_s": 3.6,
|
|
"per_stream_tok_s": [
|
|
78.8
|
|
],
|
|
"aggregate_tok_s": 71.1,
|
|
"runs": [
|
|
{
|
|
"wall_s": 3.6,
|
|
"load_s": 0.25,
|
|
"prompt_tokens": 29,
|
|
"prompt_eval_s": 0.06,
|
|
"gen_tokens": 256,
|
|
"gen_s": 3.25,
|
|
"tok_per_s": 78.8
|
|
}
|
|
]
|
|
},
|
|
"2": {
|
|
"wall_s": 7.32,
|
|
"per_stream_tok_s": [
|
|
37.6,
|
|
50.6
|
|
],
|
|
"aggregate_tok_s": 69.9,
|
|
"runs": [
|
|
{
|
|
"wall_s": 7.32,
|
|
"load_s": 0.25,
|
|
"prompt_tokens": 29,
|
|
"prompt_eval_s": 0.1,
|
|
"gen_tokens": 256,
|
|
"gen_s": 6.81,
|
|
"tok_per_s": 37.6
|
|
},
|
|
{
|
|
"wall_s": 5.99,
|
|
"load_s": 0.45,
|
|
"prompt_tokens": 29,
|
|
"prompt_eval_s": 0.41,
|
|
"gen_tokens": 256,
|
|
"gen_s": 5.06,
|
|
"tok_per_s": 50.6
|
|
}
|
|
]
|
|
},
|
|
"4": {
|
|
"wall_s": 7.49,
|
|
"per_stream_tok_s": [
|
|
50.8,
|
|
50.0,
|
|
79.7,
|
|
36.7
|
|
],
|
|
"aggregate_tok_s": 136.7,
|
|
"runs": [
|
|
{
|
|
"wall_s": 5.81,
|
|
"load_s": 0.45,
|
|
"prompt_tokens": 29,
|
|
"prompt_eval_s": 0.25,
|
|
"gen_tokens": 256,
|
|
"gen_s": 5.04,
|
|
"tok_per_s": 50.8
|
|
},
|
|
{
|
|
"wall_s": 5.72,
|
|
"load_s": 0.44,
|
|
"prompt_tokens": 29,
|
|
"prompt_eval_s": 0.1,
|
|
"gen_tokens": 256,
|
|
"gen_s": 5.12,
|
|
"tok_per_s": 50.0
|
|
},
|
|
{
|
|
"wall_s": 3.55,
|
|
"load_s": 0.25,
|
|
"prompt_tokens": 29,
|
|
"prompt_eval_s": 0.05,
|
|
"gen_tokens": 256,
|
|
"gen_s": 3.21,
|
|
"tok_per_s": 79.7
|
|
},
|
|
{
|
|
"wall_s": 7.49,
|
|
"load_s": 0.28,
|
|
"prompt_tokens": 29,
|
|
"prompt_eval_s": 0.08,
|
|
"gen_tokens": 256,
|
|
"gen_s": 6.97,
|
|
"tok_per_s": 36.7
|
|
}
|
|
]
|
|
},
|
|
"8": {
|
|
"wall_s": 11.56,
|
|
"per_stream_tok_s": [
|
|
50.5,
|
|
36.1,
|
|
80.1,
|
|
50.6,
|
|
78.6,
|
|
50.7,
|
|
50.5,
|
|
79.8
|
|
],
|
|
"aggregate_tok_s": 177.2,
|
|
"runs": [
|
|
{
|
|
"wall_s": 5.92,
|
|
"load_s": 0.43,
|
|
"prompt_tokens": 29,
|
|
"prompt_eval_s": 0.34,
|
|
"gen_tokens": 256,
|
|
"gen_s": 5.07,
|
|
"tok_per_s": 50.5
|
|
},
|
|
{
|
|
"wall_s": 7.6,
|
|
"load_s": 0.27,
|
|
"prompt_tokens": 29,
|
|
"prompt_eval_s": 0.08,
|
|
"gen_tokens": 256,
|
|
"gen_s": 7.09,
|
|
"tok_per_s": 36.1
|
|
},
|
|
{
|
|
"wall_s": 7.13,
|
|
"load_s": 0.24,
|
|
"prompt_tokens": 29,
|
|
"prompt_eval_s": 0.05,
|
|
"gen_tokens": 256,
|
|
"gen_s": 3.2,
|
|
"tok_per_s": 80.1
|
|
},
|
|
{
|
|
"wall_s": 5.85,
|
|
"load_s": 0.44,
|
|
"prompt_tokens": 29,
|
|
"prompt_eval_s": 0.28,
|
|
"gen_tokens": 256,
|
|
"gen_s": 5.06,
|
|
"tok_per_s": 50.6
|
|
},
|
|
{
|
|
"wall_s": 3.6,
|
|
"load_s": 0.25,
|
|
"prompt_tokens": 29,
|
|
"prompt_eval_s": 0.05,
|
|
"gen_tokens": 256,
|
|
"gen_s": 3.26,
|
|
"tok_per_s": 78.6
|
|
},
|
|
{
|
|
"wall_s": 11.47,
|
|
"load_s": 0.44,
|
|
"prompt_tokens": 29,
|
|
"prompt_eval_s": 0.08,
|
|
"gen_tokens": 256,
|
|
"gen_s": 5.05,
|
|
"tok_per_s": 50.7
|
|
},
|
|
{
|
|
"wall_s": 11.56,
|
|
"load_s": 0.44,
|
|
"prompt_tokens": 29,
|
|
"prompt_eval_s": 0.08,
|
|
"gen_tokens": 256,
|
|
"gen_s": 5.07,
|
|
"tok_per_s": 50.5
|
|
},
|
|
{
|
|
"wall_s": 10.67,
|
|
"load_s": 0.25,
|
|
"prompt_tokens": 29,
|
|
"prompt_eval_s": 0.05,
|
|
"gen_tokens": 256,
|
|
"gen_s": 3.21,
|
|
"tok_per_s": 79.8
|
|
}
|
|
]
|
|
}
|
|
},
|
|
"context": {
|
|
"2000": {
|
|
"wall_s": 2.82,
|
|
"load_s": 0.3,
|
|
"prompt_tokens": 1803,
|
|
"prompt_eval_s": 2.48,
|
|
"gen_tokens": 2,
|
|
"gen_s": 0.03,
|
|
"tok_per_s": 72.4,
|
|
"prompt_eval_tok_s": 727.0
|
|
},
|
|
"8000": {
|
|
"wall_s": 2.53,
|
|
"load_s": 0.27,
|
|
"prompt_tokens": 7138,
|
|
"prompt_eval_s": 2.16,
|
|
"gen_tokens": 3,
|
|
"gen_s": 0.03,
|
|
"tok_per_s": 97.2,
|
|
"prompt_eval_tok_s": 3304.6
|
|
},
|
|
"16000": {
|
|
"wall_s": 9.73,
|
|
"load_s": 0.46,
|
|
"prompt_tokens": 14248,
|
|
"prompt_eval_s": 9.06,
|
|
"gen_tokens": 3,
|
|
"gen_s": 0.05,
|
|
"tok_per_s": 61.9,
|
|
"prompt_eval_tok_s": 1572.6
|
|
}
|
|
},
|
|
"cold": {
|
|
"wall_s": 0.47,
|
|
"load_s": 0.25,
|
|
"prompt_tokens": 13,
|
|
"prompt_eval_s": 0.05,
|
|
"gen_tokens": 8,
|
|
"gen_s": 0.09,
|
|
"tok_per_s": 86.6
|
|
},
|
|
"summary": {
|
|
"warm_tok_s_median": 50.6,
|
|
"cold_load_s": 0.25,
|
|
"aggregate_tok_s_at_4": 136.7,
|
|
"scaling_4_vs_1": 1.92
|
|
}
|
|
} |