mozempkandClaude Fable 5 67c1b6b827 warmboot: self-heal crashed duo members + boot-restore guard ...

Suspend/resume kills the GPU-side duo member (CUDA context lost; often
wedged nvidia_uvm on this machine). Daemon now ticks every 60s: if
exactly one duo member is running, the missing one is reloaded via its
/upstream health endpoint and its snapshot restored. Saves stay at
5-min cadence. Boot restore skips members that are already running.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

2026-07-10 18:13:01 +02:00

..

benchmark_models.sh

Initial commit: tuned multi-model llama.cpp stack

2026-05-06 15:56:40 +02:00

benchmark.sh

Initial commit: tuned multi-model llama.cpp stack

2026-05-06 15:56:40 +02:00

cpu_ctx_test.sh

Initial commit: tuned multi-model llama.cpp stack

2026-05-06 15:56:40 +02:00

download_models.sh

Initial commit: tuned multi-model llama.cpp stack

2026-05-06 15:56:40 +02:00

duo-warmboot-daemon.sh

warmboot: self-heal crashed duo members + boot-restore guard

2026-07-10 18:13:01 +02:00

duo-warmboot.sh

swap-stack: slot KV save/restore for duo prompt caches (x570 S5 pattern)

2026-07-10 16:13:20 +02:00

expert_heatmap.py

swap-stack: duo config — qwen3-4b full GPU, ornith-35b pure CPU

2026-07-10 08:28:32 +02:00

kv_quant_test.sh

Initial commit: tuned multi-model llama.cpp stack

2026-05-06 15:56:40 +02:00

moe_bench.py

swap-stack: duo config — qwen3-4b full GPU, ornith-35b pure CPU

2026-07-10 08:28:32 +02:00

quality_test.sh

Initial commit: tuned multi-model llama.cpp stack

2026-05-06 15:56:40 +02:00

quick_bench.sh

swap-stack: duo config — qwen3-4b full GPU, ornith-35b pure CPU

2026-07-10 08:28:32 +02:00