From 2c11748f87cf4e1e5df662470bd58c7c54c8bb84 Mon Sep 17 00:00:00 2001 From: Vuong Hoang Date: Thu, 6 Aug 2026 10:42:45 -0700 Subject: [PATCH] chore(reranker): harden A3/A4 backends restart=unless-stopped (reboot survival) A3 now backs the prod reranker alias but was launched --restart no; docker update to unless-stopped so an ana-ml2 reboot can't silently break the alias. Full compose-service promotion tracked as a follow-up in the selection ledger. --- docs/pfi/reranker-selection-ledger.md | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) diff --git a/docs/pfi/reranker-selection-ledger.md b/docs/pfi/reranker-selection-ledger.md index e2a0146..ec74d89 100644 --- a/docs/pfi/reranker-selection-ledger.md +++ b/docs/pfi/reranker-selection-ledger.md @@ -201,9 +201,11 @@ on ana-ml2; `/model/delete` the two aliases (DB-persisted); weights retained in - **A2 (`vllm-rerank-a2` :8012)** + alias `reranker-a2-qwen3-seqcls` — bench-only, tear down when Brokkr signals the bake-off is closed (`docker stop/rm` + `/model/delete`). - **A4 (`vllm-rerank-a4` :8014)** + alias — KEEP for now (Brokkr's documented throughput fallback). -- **A3 (`vllm-rerank-a3` :8013)** — now PRODUCTION (backs the `reranker` alias). Promote from - throwaway `docker run` to a durable compose service when the dust settles (currently `--restart - no`, so it will NOT survive an ana-ml2 reboot — **follow-up: make A3 durable**). +- **A3 (`vllm-rerank-a3` :8013)** — now PRODUCTION (backs the `reranker` alias). Hardened + 2026-08-06: `docker update --restart unless-stopped` (survives ana-ml2 reboot, no recreate). + A4 given the same. **Remaining follow-up (not urgent): promote A3 from throwaway `docker run` + to a canonical compose service** (`stacks/vllm/`) for config-managed consistency — a recreate, + so do it in a window since it briefly drops `reranker`. - **Incumbent (`vllm-rerank` :8002)** — keep up as rollback until Brokkr/worldtree close the post-cutover watch; retire (not delete) only on explicit sign-off. - **`rerank_hybrid_floor`** — Brokkr routing to worldtree-dev directly (drop, don't re-tune).