Frank c5b55e1e3b frank-medium: GPU_UTIL 0.98 -> 0.97 — the 0.98 startup threshold sits within ~15 MiB of the free memory measured at engine init (worker HIP context + amdgpu per-boot baseline ~690 MiB), so 2026-09-26's boot crash-looped on every restart; 0.97 buys ~160 MiB headroom at ~5k KV tokens

2026-09-26 15:02:20 -07:00

..

quadlet

frank-medium: GPU_UTIL 0.98 -> 0.97 — the 0.98 startup threshold sits within ~15 MiB of the free memory measured at engine init (worker HIP context + amdgpu per-boot baseline ~690 MiB), so 2026-09-26's boot crash-looped on every restart; 0.97 buys ~160 MiB headroom at ~5k KV tokens

2026-09-26 15:02:20 -07:00

frank-medium-healthcheck.py

feat(frank-medium): cut the endpoint over to radiance TP=2

2026-09-20 18:15:27 -07:00

qwen-sharp-v22.4.0.jinja

feat(frank-medium): serve the Qwen-Sharp v22.4.0 chat template (froggeric)

2026-09-21 11:11:33 -07:00

qwen-sharp-v22.5.0.jinja

frank-medium: swap to ParoQuant MXFP6 (Swift Qwen3.8-27B) + Qwen-Sharp v22.5.0

2026-09-21 22:46:44 -07:00

radiance-entrypoint.sh

frank-medium: revert GPU_UTIL to 0.98 (0.99 is infeasible on 32 GB R9700)

2026-09-22 00:15:06 -07:00