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

..

chat_template.jinja

Add standard benchmark baseline and tuning arms

2026-10-26 17:11:43 -07:00

corpus-build.json

Add standard benchmark baseline and tuning arms

2026-10-26 17:11:43 -07:00

corpus-manifest.sha256

Add standard benchmark baseline and tuning arms

2026-10-26 17:11:43 -07:00