Files
Jason WittyandClaude Opus 5.5 d525f315f4 Add standard benchmark baseline and tuning arms
standard-v1 on the idle server: ~2,900 prompt tok/s at 16K, decode
~110-131. --adapt-async 1 neutral, --pipeline-windows 2 slower decode,
--prefill auto:32768 22% slower prompt at 16K. Setup defaults kept and
the original config restored.

Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
2026-10-26 17:11:43 -07:00

14 lines
290 B
JSON

{
"engine_options": null,
"other_engine_options": {},
"server_defaults": {
"temperature": 1.0,
"top_p": 0.95,
"top_k": 20,
"n_predict": -1
},
"total_slots": 1,
"context": 131072,
"source": "the server was already running; its engine options are not exposed"
}