Files
homelab/ansible
Hermes Agent service account 782cbe33d1 llm-inference: size ctx-size/parallel for aux task offload
Previous ctx-size=8192/parallel=4 gave 2048 tokens/slot, too small for
context compression inputs (observed live rejection at 3826 tokens).

Measured VRAM on astro-orbiter (RTX 3090 24GB): weights ~17GB resident,
~294KiB/token pool-wide for KV cache+buffers at prior sizing.

New: ctx-size=16384, parallel=2 -> 8192 tokens/slot (matches model's
native n_ctx_train max). Projected VRAM ~21.8GB, ~2.7GB headroom.

Applied directly via ansible-playbook (Semaphore currently broken --
fix tracked separately).
2026-08-05 12:14:11 -05:00
..
2025-11-21 05:48:43 -08:00
2025-11-19 09:36:59 -08:00
2025-11-19 09:36:59 -08:00