command-center/agent/memories/--home-blank-Projects-serverAppConfig--/rollout_summaries/01a10985-1eed-7260-ad2d-49a2af9c96c4-frank_primary_expert.md at 3579c7ebc5e35a7343a1c27415ca1c1823aa8ece

0 Fork 0

Files

T

Frank 5b08896e4e chore(memory): snapshot auto-learned memory and renamed workstation skills

--home-blank-.omp--: MEMORY.md +140 / learned.md / memory_summary.md /
raw_memories.md +1002 rewritten by auto-learn after the model rename,
frank-medium split-balance and bottleneck studies. Skills renamed to
single-topic buckets: dotfile-git-workflow -> ghostty-text-aa +
niri-display-rotation + noctalia-theme, handy-service-mgmt ->
handy-flm-inference, inference-runtime -> llama-cpp-parallelism.

--home-blank-Projects-serverAppConfig--: 38 new rollout summaries,
raw_memories.md/MEMORY.md refreshed, skills re-bucketed (bench-protocol,
llm-fleet-model-swap, rootless-quadlet-log-retrieval, orchestration-quadlet).

Per-worktree bucket (wt-20261006-122204) is now gitignored, not committed.

2026-10-09 13:17:53 -07:00

565 B

Raw Blame History

thread_id: 01a10985-1eed-7260-ad2d-49a2af9c96c4 updated_at: 1791176837

Documented expert arena definition levers in frank-primary vLLM fork: arena = budget - non-expert - KV_reserve(9190B/token × max_model_len) - graphs - overhead. Key levers: max_model_len (lower=increase), --expert-precise-memory (reduces overhead 7.60→5.25 GiB), VLLM_CUDAGRAPH_* env vars (graph term), gpu_memory_utilization (budget). Pool/KV_BYTES is NOT an arena lever. --expert-offload-mem controls host offload (120 GiB). Current shape G: 17.77 GiB / 7762 slots, UTIL must stay 0.982.

565 B Raw Blame History Unescape Escape

565 B

Raw Blame History