Qeravio
Canonical AI event

Llama.cpp tool now prints concise per-model results table in --models mode.

The --models mode now outputs a concise table with colored PASS/FAIL/SKIP cells. The model name is printed before each test suite runs.

25 Sept 20261 verified claims1 sources1 observations
What happened

The official source reports this update: b11154: test-save-load-state : print a per-model results table in --models mode. test-save-load-state : print a per-model results table in --models mode ( #29316 ) test-save-load-state : print a per-model results table in --models mode in --models mode the output was very heavy: every model printed its token dumps, per-test headers and PASS lines. instead, silence all logging except the table itself (common_log_set_verbosity_thold(0) leaves only LOG / LOG_LEVEL_OUTPUT) and print one row per model with one column per test, colored PASS/FAIL/SKIP cells, row by row.

Why it matters

This official update documents a development concerning b11154: test-save-load-state : print a per-model results table in --models mode. Its practical significance depends on the scope and evidence stated by the source.

What to watch next

Read the official source update and verify its stated scope, evidence and timing before acting on it.

Connected knowledge

Entities affected by this event

Continue this topic
Evidence trail

Sources behind the event