mozempkandClaude Fable 5 597b882743 swap-stack: slot KV save/restore for duo prompt caches (x570 S5 pattern) ...

--slot-save-path + --cache-reuse 256 on both duo members, ./kv-cache
mounted at /cache. Measured on ornith (3K-token system prompt): warm
prefix reuse 296ms vs 106.7s cold prefill (361x); slot save 84MB in
59ms, GDN recurrent state serializes. scripts/duo-warmboot.sh wraps
save/restore/status via llama-swap /upstream passthrough. Restore
after restart: run 'duo-warmboot.sh restore' post stack boot.

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

2026-07-10 16:13:20 +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.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