Files
hermes-agent/website/docs/user-guide
kshitij e7667e56df docs(stt): honest memory-behavior wording for idle unload
The docs promised 'frees ~370MB RAM' — measured behavior on macOS/CPU
is that ctranslate2's allocator keeps the freed pages (RSS doesn't
visibly shrink); the concrete win is VRAM release on CUDA hosts and
process-internal reuse on CPU. Say exactly that instead.
2026-08-07 19:26:12 +05:30
..
2026-08-05 21:33:44 +05:30