Ilker ManapandClaude Opus 5.5 0416b827fd ctl bench reads a guarded engine's metrics with the engine's key, or says why it cannot ...

The sampler sent the key given for --target, which for the gateway is a
client's, so llama.cpp and TensorRT-LLM refused every read and the run
reported an idle engine. The engine key now comes from the admin API for the
replica at --metrics' address, or --metrics-key; unreadable metrics stop the
run before any load, and a step that read none shows why.

Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>

2026-10-05 00:20:25 +02:00

..

eval

Quality suites, and new weights held to one: ctl eval, model update/promote --eval, model gate

2026-10-05 00:04:43 +02:00

bench_test.go

Add ctl bench, and fix two holes it walked into

2026-09-16 09:51:37 +02:00

bench.go

ctl bench reads a guarded engine's metrics with the engine's key, or says why it cannot

2026-10-05 00:20:25 +02:00

capacity.go

Keep what a benchmark found out, instead of leaving it in a terminal

2026-09-27 11:51:58 +02:00

sampler_test.go

ctl bench reads a guarded engine's metrics with the engine's key, or says why it cannot

2026-10-05 00:20:25 +02:00

sampler.go

ctl bench reads a guarded engine's metrics with the engine's key, or says why it cannot

2026-10-05 00:20:25 +02:00