picollm tested by Argusic Runner

Attempt 1 of 3 · Did not run · Argusic Score 30.0 of 100

all runs of picollmcompressionefficient-inferencegemmagenerative-ailanguage-modellanguage-models

Session recording

Loading recording...

Download the original recording · fingerprint d5d2fb842ff29adb...

What the test found

The C demos compile and link, the Python binding installs and imports, and the shared library reports version 2.1.0 with 128 max top choices and 192 CPU threads available, but no model file is present so pv_picollm_init fails on every attempted load.

C demos built, Python binding installed, library loads and reports version 2.1.0. The library requires a proprietary model file from Picovoice Console and an AccessKey for GPU activation. With device='cpu' the library skips activation entirely but still needs a valid model file. Tests require 5 different model files plus an AccessKey — none available in this environment. This is a design constraint of Picovoice's SDK, not a defect.

Argusic installed picollm in 5 minutes; verification reached Nothing verified. 0 of 1 recorded error was worked through (see the timeline below).

Did not runall runs of picollm

This summary is drawn from the agent's recorded report for this run. Every figure traces to the log and recording above; nothing here is authored.

Error and fix timeline

No errors were recorded for this run.

Discussion