feat(embed-rerank): TEI is the fleet embed/rerank engine; esh-ml1 sole backend; retire fv-ml1 seats

Prime, 2026-09-25: TEI serves embedding + reranking for esh-ml1 and the fleet
from now on; fv-ml1 retires both once esh-ml1 is up.

- stacks/embed-rerank: vLLM -> TEI 1.9.4 (89- Ada build), same ports
  8001/8013, fail-closed truncation (--auto-truncate false; embed
  --max-batch-tokens 32768).
- litellm: qwen3-embedding -> esh-ml1 only (hosted_vllm/, unchanged address);
  reranker -> huggingface/ provider at :8013 (hosted_vllm/ 422s on TEI's
  `texts` body). DB alias reranker-a3-bge-v2-m3 patched to the same target.
- Verified via the gateway against the retiring fv-ml1 seats: embed cosine
  median 0.999927 (n=203); rerank top-1/top-3 29/30.
- stacks/vllm: vllm-embed and vllm-rerank-a3 removed (containers retired on
  fv-ml1, GPU 1 freed ~6.1 GB); reward + coder unchanged.
- Bake-off record moved to docs/pfi/embed-rerank-tei-vs-vllm-bakeoff.md;
  CLAUDE.md gains the TEI convention.

CLAUDE.md

@@ -331,6 +331,10 @@ Observed and standardized across servers:
   the new content serves immediately — it is the route table that is frozen at
   start, not the file contents. Reference it as `icon: /images/<file>`.
 - **Healthchecks** on services that expose HTTP
+- **Embedding + reranking models are served with Hugging Face TEI, not vLLM** (Prime,
+  2026-09-25). The fleet service is `stacks/embed-rerank` on esh-ml1. Why, plus the
+  parity bar any engine or model change must clear:
+  `docs/pfi/embed-rerank-tei-vs-vllm-bakeoff.md`.
 
 ## Servers
 
@@ -362,7 +366,7 @@ Observed and standardized across servers:
 | esh-pve | 10.0.250.35 | ESH home lab | Proxmox VE hypervisor | `servers/esh-pve/README.md` |
 | esh-pve-nas | 10.0.50.55 | ESH home lab | Proxmox VE hypervisor (storage / media) | `servers/esh-pve-nas/README.md` |
 | esh-vm-db | 10.0.50.60 | ESH home lab | DB VM — PostgreSQL (paperless-ng) + MongoDB; bare-metal VM, no Docker | `servers/esh-vm-db/README.md` |
-| esh-ml1 | 10.0.50.80 | ESH home lab | GPU LXC (CT 110 on esh-pve, RTX 2000E Ada 16 GB, host-side NVIDIA driver) — embedding + reranking, LiteLLM order-2 failover behind fv-ml1 | `servers/esh-ml1/README.md` |
+| esh-ml1 | 10.0.50.80 | ESH home lab | GPU LXC (CT 110 on esh-pve, RTX 2000E Ada 16 GB, host-side NVIDIA driver) — **the fleet's embedding + reranking service** (TEI), sole gateway backend since 2026-09-25 | `servers/esh-ml1/README.md` |
 
 **Placement rules:**
 - GPU-required stacks → `fv-ml1` (primary, Fountain Valley) or `irv-ml1`

docs/fleettools/litellm.md

@@ -33,8 +33,8 @@ on someone else's tab" matters, get a project-scoped key.
 `summarizer` / `summarizer-large` / `classifier` — the always-available local seat for
 summarization, naming/labeling, classification and triage. Essentially free compute;
 reach for it before spending premium API tokens on work a small local model handles.
-Embeddings and rerankers (`qwen3-embedding`, `qwen3-reranker`, `reranker`) are local
+Embeddings and reranking (`qwen3-embedding`, `reranker`) are local and free too —
-and free too. Anything named `*-frontier`, `glm-*` or `kimi-*` is **PAID**.
+served by TEI on esh-ml1 since 2026-09-25 (`qwen3-reranker` was retired 2026-08-20). Anything named `*-frontier`, `glm-*` or `kimi-*` is **PAID**.
 
 ## Traps
 

docs/pfi/embed-rerank-tei-vs-vllm-bakeoff.md

@@ -1,10 +1,16 @@
-# tei-bakeoff — TEI vs vLLM for embedding + reranking on esh-ml1
+# Embed/rerank engine bake-off — TEI vs vLLM on esh-ml1 (2026-09-25)
 
 Prime, 2026-09-25: *"run the TEI bake-off."* Hugging Face **Text Embeddings
-Inference 1.9.4** (`89-1.9.4`, the Ada build) serving the same two models as
+Inference 1.9.4** (`89-1.9.4`, the Ada build) served the same two models as the
-[`embed-rerank`](../embed-rerank/) (vLLM v0.24.0), side by side on the same RTX
+then-vLLM `embed-rerank` stack (vLLM v0.24.0), side by side on the same RTX 2000E
-2000E Ada. Not wired into the gateway. This stack either becomes the
+Ada, as a temporary `tei-bakeoff` stack.
-embed-rerank stack or is torn down.
+
+**Outcome (Prime, 2026-09-25): "TEI is embed/reranker server for esh-ml1 and the
+FLEET in general, in future."** The same day TEI replaced vLLM in
+[`stacks/embed-rerank`](../../stacks/embed-rerank/) on ports 8001/8013. The
+gateway was repointed with esh-ml1 as the sole backend, and fv-ml1's
+`vllm-embed` + `vllm-rerank-a3` seats were retired, freeing ~6.1 GB on fv-ml1
+GPU 1. The bake-off stack was removed; this file is its record.
 
 ## Results (2026-09-25 0744–0805 PT)
 
@@ -58,7 +64,7 @@ On-box, 2 interleaved runs × 3 reps each, medians:
 TEI ran its fused `FlashQwen3` path. `--max-batch-tokens 32768` did not change
 the novel time (39–40 s), so it stays at the default. **Through the gateway these
 gaps mostly vanish**: LiteLLM is the bottleneck there (see
-`servers/esh-ml1/README.md`).
+[`servers/esh-ml1/README.md`](../../servers/esh-ml1/README.md)).
 
 ### Footprint — TEI is much lighter
 

docs/pfi/fv-ml1-gpu-seat-inventory.md

@@ -124,8 +124,6 @@ context.
 | `gen-small-reasoning` | 8026 |
 | `image-judge` | 8022 |
 | `qwen-image-bench` | 8022 |
-| `qwen3-embedding` | 8001 |
-| `reranker` | 8013 |
 | `sec` | 8025 |
 | `sec-reasoning` | 8025 |
 | `summarizer` | 8026 |
@@ -138,3 +136,7 @@ context.
 *Regenerate with `scripts/seat-inventory.py` after ANY seat change —
 model swap, quant change, context or utilization edit, or speculative-decoding
 change. Run `--check` in CI to catch a stale document.*
+
+> **2026-09-25:** `qwen3-embedding` (:8001) and `reranker` (:8013) LEFT fv-ml1 —
+> their vLLM seats were retired and the names now route to TEI on esh-ml1
+> (`stacks/embed-rerank`). ~6.1 GB freed on GPU 1.

docs/pfi/reranker-selection-ledger.md

@@ -243,3 +243,12 @@ on fv-ml1; `/model/delete` the two aliases (DB-persisted); weights retained in H
   form, not load-balancing: fv-ml1 serves every request while it is up. Parity: |score|
   FV-vs-ESH max 0.000145 vs FV-vs-FV floor 0.000181, identical ranking over 11 documents.
   See `servers/esh-ml1/README.md`.
+
+## 2026-09-25 — the reranker moved to TEI on esh-ml1 (Prime)
+
+- TEI adopted as the fleet embed/rerank engine after a bake-off
+  (`docs/pfi/embed-rerank-tei-vs-vllm-bakeoff.md`). `vllm-rerank-a3` on fv-ml1 was
+  **retired**; `reranker` and the DB alias `reranker-a3-bge-v2-m3` now both route to
+  `tei-rerank` on esh-ml1 :8013 via LiteLLM's `huggingface/` provider. Same model
+  (bge-reranker-v2-m3): top-1/top-3 identical to the retired seat, and scores move
+  up to 0.019 in the near-zero tail.

persistent-memory.d/2026-09-25-tei-fleet-embed-rerank.md

@@ -0,0 +1,43 @@
+# `[2026-09-25]` TEI adopted as the fleet embed/rerank engine; esh-ml1 is the sole backend; fv-ml1 seats retired
+
+**Prime's rulings (2026-09-25):**
+- Utility seats move off fv-ml1 to a utility host like esh-ml1, accepting slower
+  service; the Blackwells are kept for higher-requirement work.
+- **parakeet STAYS on fv-ml1** (real-time chat path, every ms counts).
+- **"TEI is embed/reranker server for esh-ml1 and the FLEET in general, in
+  future."**
+- fv-ml1 retires both embed + rerank once esh-ml1 is up. A **second RTX 2000 is
+  coming to the fleet soon**; until then embed/rerank has one backend (accepted).
+
+**Evidence chain:** speed A/B vs fv-ml1 (single queries a wash, bulk 3–10×
+slower on the Ada); whole-novel test (*The Stand*, 12,814 paragraphs) through
+the gateway ~12 min one per request on either site, because the gateway is the
+bottleneck; TEI bake-off (`docs/pfi/embed-rerank-tei-vs-vllm-bakeoff.md`):
+matches vLLM vectors, no re-embed, slower on bulk, much lighter. Dvalin
+(Grok research peer) reviewed: agree with caveats. Two caveats were actioned:
+fail-closed truncation (TEI's default silently embedded a 16,384-token prefix of a
+40k input and returned 200) and nevermore's 0.3 rerank threshold (0 flips in 2,000
+scores; low sensitivity, since few scores sit near 0.3).
+
+**Cut-over, 0820–0830 PT:**
+1. esh-ml1: vLLM pair down, TEI `tei-embed` :8001 + `tei-rerank` :8013 up (same
+   ports). The old `.env` is kept as `.env.vllm-retired-2026-09-25`. The vLLM image
+   (~30 GB) is kept in case the reward classifier (vLLM-only) moves here.
+2. Gateway: `qwen3-embedding` → esh-ml1 only (`hosted_vllm/`, unchanged
+   address); `reranker` → **`huggingface/`** provider (hosted_vllm 422s on TEI's
+   `texts` body); `order` fields removed; LiteLLM restarted (~58 s). The DB
+   alias `reranker-a3-bge-v2-m3` was PATCHed to the same TEI target.
+3. Verified through the gateway against the still-running FV seats: embed
+   cosine median 0.999927 / min 0.999881 (n=203); rerank top-1/top-3 29/30 (2 of
+   30 lists had a duplicate-source tie; the disagreeing query wasn't logged).
+4. **No direct (non-gateway) consumers existed**: per day, fv-ml1 seat POSTs =
+   gateway spend-log rows exactly (09-20→09-24). After the repoint, the only FV hits
+   were my own verification calls.
+5. fv-ml1: `vllm-embed` + `vllm-rerank-a3` stopped and removed; `stacks/vllm`
+   compose + `.env.example` updated (reward + coder untouched, 10–11 days up);
+   GPU 1 93,086 → 86,956 MiB (~6.1 GB freed).
+
+**Open:** esh-ml1 is now load-bearing with no monitoring (no Beszel, Kuma or
+Homepage). Next: "what else moves". vllm-reward (9.2 GB, vLLM-only) is the
+candidate and fits beside TEI's ~2.6 GB on 16 GB; vllm-coder (6.3 GB) is
+latency-sensitive.

persistent-memory.md

@@ -117,14 +117,13 @@ no longer deployed sidecars here. See Recent decisions.)
 
 _As of 2026-09-24 ~2245 PT._
 
-### ⭐ esh-ml1: TEI vs vLLM decision pending (Prime), then "what else moves"
+### ⭐ TEI is the fleet embed/rerank engine; esh-ml1 is the SOLE backend (2026-09-25)
 
-Prime's direction 2026-09-25: move the utility seats off fv-ml1 to esh-ml1
+Cut-over done 0830 PT: gateway `qwen3-embedding` + `reranker` (+ DB alias a3) →
-(accepting slower); **parakeet STAYS on fv-ml1** (real-time chat path). TEI
+TEI on esh-ml1; fv-ml1's two vLLM seats retired. ⚠ **Single backend until the
-bake-off done — results `stacks/tei-bakeoff/README.md`; tei-embed :8081 +
+second RTX 2000 arrives**, and **esh-ml1 has no monitoring yet**: wire Beszel +
-tei-rerank :8083 running beside vLLM, NOT gateway-wired. Next: Prime picks the
+Kuma next. Next conversation with Prime: "what else moves" (vllm-reward is the
-engine, then the rest of the move (reward model is the open candidate; it needs
+candidate; **parakeet stays**). → Recent decisions.
-vLLM — TEI can't serve a Llama classifier).
 
 ### ✅ esh-ml1 built (2026-09-24) — two follow-ups
 
@@ -170,6 +169,7 @@ a shutdown (stays off by design). Outcomes and revert in
 
 ## Recent decisions
 
+- `[2026-09-25]` **TEI adopted as the fleet embed/rerank engine (Prime); esh-ml1 is the sole gateway backend for `qwen3-embedding` + `reranker`; fv-ml1's vLLM embed/rerank seats retired (~6.1 GB freed); parakeet stays on fv-ml1.** → `persistent-memory.d/2026-09-25-tei-fleet-embed-rerank.md`
 - `[2026-09-24]` **esh-ml1 built — RTX 2000E Ada as CT 110 on esh-pve (host driver 580.178.04 DKMS, loaded live, no reboot), vLLM embed+rerank at measured parity with fv-ml1, wired as LiteLLM `order: 2` failover; dead DB alias `reranker-a3-bge-v2-m3` (pre-relocation IP) repaired.** → `persistent-memory.d/2026-09-24-esh-ml1-embed-rerank.md`
 - `[2026-09-24]` **esh-pve: VM 102 retired, a 14-day hung VFIO process found and cleared, T400 → RTX 2000 Ada; Prime chose LXC + host driver for embed/rerank** (implementation deferred to next session, tracked here + `servers/esh-pve/README.md`). → `persistent-memory.d/2026-09-24-esh-pve-vm102-retired-gpu-swap.md`
 - `[2026-09-24]` **pfi-gx10 AC-restore UEFI patch applied but NOT validated; box OFF until Prime's AC pull 2026-09-25** (tracking: `servers/pfi-gx10/README.md`, `e5197a3`). → `persistent-memory.d/2026-09-24-gx10-ac-restore-patch.md`

playbooks/esh-ml1-lxc.yaml

@@ -59,7 +59,7 @@ steps:
         --onboot 1 --startup order=30,up=10 \
         --dev0 /dev/nvidia0 --dev1 /dev/nvidiactl \
         --dev2 /dev/nvidia-uvm --dev3 /dev/nvidia-uvm-tools \
-        --description "esh-ml1 — RTX 2000E Ada embedding + reranking (vLLM). Built by eshpfi playbooks/esh-ml1-lxc.yaml; stack stacks/embed-rerank. NOT in the vzdump job on purpose (rebuildable)."
+        --description "esh-ml1 — RTX 2000E Ada: the fleet embedding + reranking service (TEI). Built by eshpfi playbooks/esh-ml1-lxc.yaml; stack stacks/embed-rerank. NOT in the vzdump job on purpose (rebuildable)."
     when: "! pct status {{ ctid }} >/dev/null 2>&1"
 
   - name: Start the container

servers/esh-ml1/README.md

@@ -1,8 +1,14 @@
 # esh-ml1
 
 GPU LXC for the ESH home lab: **CT 110 on esh-pve**, holding the **NVIDIA RTX
-2000E Ada** (16 GB, 50 W, `01:00.0`). It serves the fleet's embedding and
+2000E Ada** (16 GB, 50 W, `01:00.0`). **It is the fleet's embedding and
-reranking models locally at ESH. Built 2026-09-24.
+reranking service** — the only backend behind the gateway's `qwen3-embedding`,
+`reranker` and `reranker-a3-bge-v2-m3` since 2026-09-25. Built 2026-09-24.
+
+⚠ **Single backend until the second RTX 2000 arrives** (Prime, 2026-09-25). If
+esh-ml1, esh-pve, or ESH's mesh route (esh-scale, CT 108) is down, fleet
+embeddings and reranking are down: Worldtree recall, nevermore clustering, Open
+WebUI RAG.
 
 | | |
 |---|---|
@@ -16,17 +22,31 @@ reranking models locally at ESH. Built 2026-09-24.
 
 ## What it serves
 
-`stacks/embed-rerank` (`/opt/docker/compose/embed-rerank`):
+`stacks/embed-rerank` (`/opt/docker/compose/embed-rerank`), **Hugging Face TEI
+1.9.4** — the fleet's embed/rerank engine from 2026-09-25 (Prime). It replaced
+vLLM here after a bake-off; see
+[`docs/pfi/embed-rerank-tei-vs-vllm-bakeoff.md`](../../docs/pfi/embed-rerank-tei-vs-vllm-bakeoff.md).
 
-| container | model | port | gateway name |
+| container | model | port | gateway name (LiteLLM provider) |
 |---|---|---|---|
-| `vllm-embed` | `Qwen/Qwen3-Embedding-0.6B` | 8001 | `qwen3-embedding` (order 2) |
+| `tei-embed` | `Qwen/Qwen3-Embedding-0.6B` | 8001 | `qwen3-embedding` (`hosted_vllm/`, `/v1`) |
-| `vllm-rerank-bge` | `BAAI/bge-reranker-v2-m3` | 8013 | `reranker` (order 2) |
+| `tei-rerank` | `BAAI/bge-reranker-v2-m3` | 8013 | `reranker`, `reranker-a3-bge-v2-m3` (`huggingface/`, no `/v1`) |
 
-The same models, vLLM version (`v0.24.0`, digest `251eba5cc7c1`) and flags as
+VRAM ~2.6 GB for both; the rest of the 16 GB is free for further utility seats.
-fv-ml1's `vllm` stack, so the two sites are interchangeable. In LiteLLM they
+The vLLM image (`vllm/vllm-openai:v0.24.0`, ~30 GB) is still on disk: kept in
-are the **order-2 failover** behind fv-ml1: fv-ml1 serves every request while
+case a vLLM-only seat (the reward classifier) moves here.
-it is up.
+
+**Cut-over verified 2026-09-25** through the gateway against fv-ml1's vLLM seats
+just before they were retired: embed cosine median 0.999927 / min 0.999881
+(n=203); rerank top-1 and top-3 agreement 29/30. Two of the 30 lists contained
+the source paragraph twice, which makes #1 a tie either engine may break either
+way. The disagreeing query wasn't logged, so that is the likely cause, not a
+proven one.
+
+### History — the vLLM era (2026-09-24 → 25)
+
+These measurements are of vLLM on this card vs vLLM on fv-ml1, and are kept for
+reference.
 
 **Parity, measured 2026-09-24** (11 texts incl. CJK, code, a 6k-char passage;
 2 runs per site):
@@ -62,7 +82,7 @@ on small-query latency on fv-ml1, so the small-query rows cannot rank the sites.
 Positive control: 2k-token inputs were slower than 512-token ones on both
 sites. One fv-ml1 rep of the gateway-vantage rerank burst stalled to 1.0 req/s
 (64 requests in ~64 s); it did not recur in 11 other reps — unexplained, n=1.
-**Consequence: keep esh-ml1 as failover, don't load-share** — sharing would
+**Consequence at the time: keep esh-ml1 as failover, don't load-share** (superseded 2026-09-25 by the move) — sharing would
 roughly double rerank latency for half the fleet's calls.
 
 **Whole-novel embedding, measured 2026-09-25 0653–0717 PT** — *The Stand*
@@ -113,10 +133,15 @@ build and this CT will fail to start at the next boot.
 
 ## Not yet wired
 
+⚠ **esh-ml1 became load-bearing on 2026-09-25, so these are no longer
+optional.** Nothing alerts if it dies today. The gateway will just start
+returning errors for `qwen3-embedding` and `reranker`.
+
+- **Beszel**: no agent yet.
+- **Uptime Kuma**: no check on `:8001/health` / `:8013/health` yet.
 - **Homepage**: the compose carries labels, but esh-ml1 is not in
   `stacks/homepage/conf/docker.yaml` (it would need dockerd on tcp/2375 like
   the other hosts).
-- **Beszel**: no agent yet.
+- **Path:** every consumer reaches esh-ml1 through the gateway at ana-docker, so
-- **ESH consumers** (Open WebUI RAG, Paperless) still go through the gateway
+  ESH callers hairpin ESH → Anaheim → ESH over the mesh. A mesh outage cuts
-  at ana-docker, so they do not survive a mesh outage. See persistent-memory
+  every consumer off, the ones at ESH included.
-  for the open decision.

stacks/embed-rerank/.env.example

@@ -1,29 +1,19 @@
-# embed-rerank tunables (esh-ml1). Copy to `.env` on the server.
+# embed-rerank tunables (esh-ml1, TEI). Copy to `.env` on the server.
-#
-# Everything model-shaped here MUST match fv-ml1's stacks/vllm .env: the same
-# models, the same vLLM version, the same max-model-len. A drift in the
-# embedding model or its version makes this seat's vectors incompatible with
-# every index built against fv-ml1's.
 
-# PINNED to fv-ml1's version. Bump both sites together.
+# TEI image tag. `89-` = the Ada Lovelace (sm_89) build; a different GPU
-VLLM_VERSION=v0.24.0
+# generation needs a different prefix (see the TEI README's image table).
+# PINNED to an exact release.
+TEI_TAG=89-1.9.4
 
-# Same host ports as fv-ml1 (container listens on 8000).
+# Kept from the vLLM era so the embedding gateway entry did not have to change.
 EMBED_PORT=8001
 RERANK_PORT=8013
 
+# ⚠ Changing EMBED_MODEL invalidates every index built on it.
 EMBED_MODEL=Qwen/Qwen3-Embedding-0.6B
 RERANK_MODEL=BAAI/bge-reranker-v2-m3
 
-# Fractions of the RTX 2000E Ada's 16,380 MiB. fv-ml1 runs 0.03 of a 96 GB
+MAX_CLIENT_BATCH_SIZE=128
-# card (~2.9 GB each); 0.20 here is ~3.2 GB each — the same budget plus a
-# little, leaving ~9.5 GB free.
-EMBED_GPU_MEM_UTIL=0.20
-RERANK_GPU_MEM_UTIL=0.20
-EMBED_MAX_MODEL_LEN=8192
-RERANK_MAX_MODEL_LEN=8192
 
-# fv-ml1's seats run with no API key (LiteLLM fronts them); match that.
-API_KEY=
 # Both models are public; no token needed.
 HF_TOKEN=

stacks/embed-rerank/README.md

@@ -1,18 +1,40 @@
 # embed-rerank
 
-The fleet's embedding + reranking models on **esh-ml1** (CT 110 on esh-pve,
+**The fleet's embedding + reranking service**, on **esh-ml1** (CT 110 on esh-pve,
-RTX 2000E Ada). The second site for `qwen3-embedding` and `reranker`; fv-ml1's
+RTX 2000E Ada), served by **Hugging Face Text Embeddings Inference (TEI)**.
-[`vllm`](../vllm/) stack is the first.
+Since 2026-09-25 it is the only backend behind the gateway names
+`qwen3-embedding`, `reranker` and `reranker-a3-bge-v2-m3`.
 
-| container | model | port |
+**TEI is the fleet's embed/rerank engine** (Prime, 2026-09-25). New embedding or
-|---|---|---|
+reranking seats go on TEI, not vLLM. Why, and the measurements behind it:
-| `vllm-embed` | `Qwen/Qwen3-Embedding-0.6B` | 8001 |
+[`docs/pfi/embed-rerank-tei-vs-vllm-bakeoff.md`](../../docs/pfi/embed-rerank-tei-vs-vllm-bakeoff.md).
-| `vllm-rerank-bge` | `BAAI/bge-reranker-v2-m3` | 8013 |
 
-**Keep it in lockstep with `stacks/vllm`:** same models, same `VLLM_VERSION`,
+| container | model | port | endpoint |
-same `--max-model-len`. The LiteLLM groups treat the two sites as one model,
+|---|---|---|---|
-so any drift in the embedding model or its version silently mixes
+| `tei-embed` | `Qwen/Qwen3-Embedding-0.6B` | 8001 | `/v1/embeddings` (OpenAI), `/embed` |
-incompatible vectors into consumers' indexes.
+| `tei-rerank` | `BAAI/bge-reranker-v2-m3` | 8013 | `/rerank` — body `{"query", "texts"}` |
+
+## Gateway wiring (stacks/litellm/conf/config.yaml)
+
+- `qwen3-embedding` → `hosted_vllm/Qwen/Qwen3-Embedding-0.6B`, `api_base: http://10.0.50.80:8001/v1`.
+- `reranker` → **`huggingface/`**`BAAI/bge-reranker-v2-m3`, `api_base: http://10.0.50.80:8013` (**no `/v1`**).
+  ⚠ `hosted_vllm/` sends `documents` and TEI answers **422 "missing field texts"**.
+- `reranker-a3-bge-v2-m3` is a DB-only alias (not in config.yaml) with the same target.
+
+## ⚠ Invariants
+
+- **Changing `EMBED_MODEL` invalidates every index built on it** (Worldtree,
+  nevermore, Open WebUI). An engine change is allowed only with a parity
+  measurement against the current vectors. The TEI switch measured cosine median
+  0.999925 and old-index retrieval overlap 0.988.
+- **Truncation is fail-closed** (`--auto-truncate false`). TEI's default silently
+  embeds a prefix of an over-length input and returns 200. Now: embed rejects
+  more than 32,768 tokens and rerank more than 8,192, both with 422.
+- **The image tag is GPU-generation specific**: `89-` is Ada. A different card
+  needs a different prefix (TEI README image table).
+- nevermore thresholds rerank scores at 0.3. TEI scores differ from the old vLLM
+  seat by up to 0.019, which produced 0 flips in 2,000 scores. Recheck
+  thresholding consumers after any engine or version change.
 
 ## Deploy
 
@@ -30,8 +52,5 @@ Host prerequisites (driver, LXC, docker, toolkit) are in
 curl -s http://10.0.50.80:8001/v1/embeddings -H 'content-type: application/json' \
   -d '{"model":"Qwen/Qwen3-Embedding-0.6B","input":"hello"}' | jq '.data[0].embedding | length'   # 1024
 curl -s http://10.0.50.80:8013/rerank -H 'content-type: application/json' \
-  -d '{"model":"BAAI/bge-reranker-v2-m3","query":"cat","documents":["a cat","a car"]}' | jq '.results[0]'
+  -d '{"query":"cat","texts":["a cat","a car"]}'                      # index 0 scores ~0.9986
 ```
-
-Parity against fv-ml1 is recorded in the host README; re-measure after any
-version bump on either side.

stacks/embed-rerank/compose.yaml

@@ -1,63 +1,66 @@
-# embed-rerank — the fleet's embedding + reranking models, served locally at ESH
+# embed-rerank — THE fleet's embedding + reranking service, on esh-ml1 (CT 110 on
-# on esh-ml1 (CT 110 on esh-pve, RTX 2000E Ada, 16 GB).
+# esh-pve, RTX 2000E Ada, 16 GB). Served by Hugging Face Text Embeddings
+# Inference (TEI).
 #
-# WHY: Prime's decision 2026-09-24 — the Ada card offloads embedding and
+# Prime, 2026-09-25: "TEI is embed/reranker server for esh-ml1 and the FLEET in
-# reranking so ESH consumers (Open WebUI RAG, Paperless) are not tied to one
+# general, in future." It replaced vLLM here the same day, after a side-by-side
-# seat on fv-ml1. It serves the SAME models as fv-ml1's `vllm` stack, with the
+# bake-off on this card (docs/pfi/embed-rerank-tei-vs-vllm-bakeoff.md). TEI
-# SAME vLLM version and flags, because embedding vectors are model-specific:
+# gives the same vectors as the old vLLM seats (no re-embedding), but it is
-# a different embedding model here would silently poison every index built
+# ~1.3x slower on bulk work on this card. It is much lighter (2.6 GB VRAM for
-# against fv-ml1's. Mirror stacks/vllm/compose.yaml when that changes.
+# both, 8 GB image, ~4 s restart). fv-ml1's vLLM embed/rerank seats were
+# retired after this went live.
 #
-#   vllm-embed        Qwen/Qwen3-Embedding-0.6B  → /v1/embeddings   :8001
+#   tei-embed    Qwen/Qwen3-Embedding-0.6B → /v1/embeddings (OpenAI), /embed  :8001
-#   vllm-rerank-bge   BAAI/bge-reranker-v2-m3    → /rerank, /score  :8013
+#   tei-rerank   BAAI/bge-reranker-v2-m3   → /rerank  (body: query + texts)   :8013
 #
-# Ports match fv-ml1 on purpose, so a LiteLLM deployment for either site
+# Ports kept from the vLLM era (and fv-ml1), so the embedding gateway entry did
-# differs only in the host part of api_base.
+# not change address. ⚠ The RERANK gateway entry must use LiteLLM's
+# `huggingface/` provider: `hosted_vllm/` sends `documents` and TEI answers 422
+# "missing field texts".
 #
-# `vllm-rerank-bge`, not fv-ml1's `vllm-rerank-a3`: that name carries R43
+# ⚠ Embedding vectors are model-specific. Never change EMBED_MODEL without a
-# bake-off provenance for THAT container; and plain `vllm-rerank` was the
+# re-embedding plan for every index built on it (Worldtree, nevermore, Open WebUI).
-# retired Qwen3-Reranker that measured harmful. Name the model instead.
 #
-# NO `tnet`/traefik-net: esh-ml1 runs no traefik, and an external network
+# FAIL-CLOSED truncation (--auto-truncate false). TEI's default silently
-# that does not exist would stop the stack from starting. Consumers reach the
+# embedded the first 16,384 tokens of a ~40k-token input and returned 200.
-# published ports directly.
+# Turning it off requires --max-batch-tokens >= the model's max input (32,768
+# for Qwen3-Embedding), or TEI refuses to start.
 #
-# Host setup (driver, LXC, docker, toolkit): playbooks/esh-pve-nvidia-host.yaml
+# NO `tnet`/traefik-net: esh-ml1 runs no traefik; consumers reach the published
-# then playbooks/esh-ml1-lxc.yaml. Tunables live in .env — edit that, not this.
+# ports, and in practice only the LiteLLM gateway does (verified from the seats'
+# logs 2026-09-25: every request matched a gateway spend-log row).
+#
+# Host setup: playbooks/esh-pve-nvidia-host.yaml, then playbooks/esh-ml1-lxc.yaml.
+# Tunables live in .env.
 
 name: embed-rerank
 
 services:
-  vllm-embed:
+  tei-embed:
-    image: vllm/vllm-openai:${VLLM_VERSION}
+    image: ghcr.io/huggingface/text-embeddings-inference:${TEI_TAG}
-    container_name: vllm-embed
+    container_name: tei-embed
     restart: unless-stopped
-    ipc: host
     ports:
-      - "${EMBED_PORT}:8000"
+      - "${EMBED_PORT}:80"
     volumes:
-      - /opt/aimodels/huggingface:/hfcache
+      - /opt/aimodels/tei-cache:/data
     environment:
-      - HF_HOME=/hfcache
+      - HF_TOKEN=${HF_TOKEN:-}
-      - HF_HUB_CACHE=/hfcache/hub
-      - HUGGING_FACE_HUB_TOKEN=${HF_TOKEN:-}
-      - VLLM_API_KEY=${API_KEY:-}
     command:
+      - --model-id
       - ${EMBED_MODEL}
       - --served-model-name
       - ${EMBED_MODEL}
-      - --runner
+      # TEI on CUDA is float16-only; parity vs the bf16 vLLM vectors was measured.
-      - pooling
-      - --host
-      - 0.0.0.0
-      - --port
-      - "8000"
-      - --gpu-memory-utilization
-      - ${EMBED_GPU_MEM_UTIL}
-      - --max-model-len
-      - ${EMBED_MAX_MODEL_LEN}
       - --dtype
-      - auto
+      - float16
+      # Default 32; vLLM had no cap and callers batch 64.
+      - --max-client-batch-size
+      - "${MAX_CLIENT_BATCH_SIZE}"
+      - --auto-truncate
+      - "false"
+      - --max-batch-tokens
+      - "32768"
     deploy:
       resources:
         reservations:
@@ -66,49 +69,39 @@ services:
               device_ids: ["0"]
               capabilities: [gpu]
     healthcheck:
-      test: ["CMD", "curl", "-f", "http://localhost:8000/health"]
+      test: ["CMD", "curl", "-fsS", "http://localhost:80/health"]
       interval: 30s
       timeout: 10s
       retries: 3
-      start_period: 180s
+      start_period: 60s
     labels:
       - homepage.group=AI - Eval & Retrieval
-      - homepage.name=vLLM Embed (esh-ml1)
+      - homepage.name=Embed — Qwen3 0.6B (TEI, esh-ml1)
       - homepage.icon=mdi-vector-arrange-below
-      - homepage.description=Qwen3 Embedding 0.6B via vLLM (esh-ml1, RTX 2000E Ada)
+      - homepage.description=Fleet embeddings (qwen3-embedding) via TEI on esh-ml1
       - homepage.href=http://10.0.50.80:${EMBED_PORT}/docs
 
-  vllm-rerank-bge:
+  tei-rerank:
-    image: vllm/vllm-openai:${VLLM_VERSION}
+    image: ghcr.io/huggingface/text-embeddings-inference:${TEI_TAG}
-    container_name: vllm-rerank-bge
+    container_name: tei-rerank
     restart: unless-stopped
-    ipc: host
     ports:
-      - "${RERANK_PORT}:8000"
+      - "${RERANK_PORT}:80"
     volumes:
-      - /opt/aimodels/huggingface:/hfcache
+      - /opt/aimodels/tei-cache:/data
     environment:
-      - HF_HOME=/hfcache
+      - HF_TOKEN=${HF_TOKEN:-}
-      - HF_HUB_CACHE=/hfcache/hub
-      - HUGGING_FACE_HUB_TOKEN=${HF_TOKEN:-}
-      - VLLM_API_KEY=${API_KEY:-}
     command:
+      - --model-id
       - ${RERANK_MODEL}
-      - --served-model-name
-      - ${RERANK_MODEL}
-      - --runner
-      - pooling
-      # bge-reranker-v2-m3 is natively a cross-encoder; no --hf-overrides.
-      - --host
-      - 0.0.0.0
-      - --port
-      - "8000"
-      - --gpu-memory-utilization
-      - ${RERANK_GPU_MEM_UTIL}
-      - --max-model-len
-      - ${RERANK_MAX_MODEL_LEN}
       - --dtype
-      - auto
+      - float16
+      - --max-client-batch-size
+      - "${MAX_CLIENT_BATCH_SIZE}"
+      # Fail-closed; bge-reranker-v2-m3's max input (8,192) fits the default
+      # max-batch-tokens (16,384).
+      - --auto-truncate
+      - "false"
     deploy:
       resources:
         reservations:
@@ -117,14 +110,14 @@ services:
               device_ids: ["0"]
               capabilities: [gpu]
     healthcheck:
-      test: ["CMD", "curl", "-f", "http://localhost:8000/health"]
+      test: ["CMD", "curl", "-fsS", "http://localhost:80/health"]
       interval: 30s
       timeout: 10s
       retries: 3
-      start_period: 180s
+      start_period: 60s
     labels:
       - homepage.group=AI - Eval & Retrieval
-      - homepage.name=vLLM Rerank bge-v2-m3 (esh-ml1)
+      - homepage.name=Rerank — bge-v2-m3 (TEI, esh-ml1)
       - homepage.icon=mdi-sort-variant
-      - homepage.description=bge-reranker-v2-m3 via vLLM (esh-ml1, RTX 2000E Ada)
+      - homepage.description=Fleet reranker (reranker) via TEI on esh-ml1
       - homepage.href=http://10.0.50.80:${RERANK_PORT}/docs

stacks/litellm/conf/config.yaml

@@ -7,8 +7,8 @@
 #
 # Model-name → upstream mapping:
 #   phi4-mini        → vLLM :8004  (generative chat)
-#   qwen3-embedding  → vLLM :8001  (/v1/embeddings)
+#   qwen3-embedding  → TEI on esh-ml1 :8001  (/v1/embeddings)
-#   qwen3-reranker   → vLLM :8002  (/rerank)
+#   reranker         → TEI on esh-ml1 :8013  (/rerank, huggingface/ provider)
 #   *  (wildcard)    → llama-swap :9292  (the swappable generative zoo)
 #
 # The wildcard fronts llama-swap so its whole model zoo logs through the
@@ -443,31 +443,21 @@ model_list:
   #     explicitly. Operator ruling 2026-08-23. ---
 
   # --- Qwen3 embeddings ---
-  # TWO deployments, one name, ordered: fv-ml1 serves (order 1); esh-ml1 takes
+  # ONE backend: esh-ml1 (RTX 2000E Ada), served by Hugging Face TEI — the fleet's
-  # over only when fv-ml1 fails (order 2 — LiteLLM's order-based fallback, v1.97
+  # embed/rerank engine from 2026-09-25 (Prime). fv-ml1's vLLM seat was retired the
-  # router.py). Same model, same vLLM version and flags at both sites, so the
+  # same day. TEI's /v1/embeddings is OpenAI-compatible, so the provider stays
-  # vectors are interchangeable: measured 2026-09-24, cosine FV-vs-ESH median
+  # `hosted_vllm/`. Same model as before; TEI vectors match the old vLLM ones
-  # 0.999908 (min 0.999772) over 11 texts, inside the FV-vs-FV self-noise floor
+  # (cosine median 0.999925, inside vLLM's own noise; old-index retrieval overlap
-  # (median 0.999927, min 0.999791); different-text negative control 0.07–0.38.
+  # 0.988 vs 0.986 self-noise), so no index needed re-embedding.
-  # ⚠ Failover cost, measured n=3 each: primary REFUSING → +0.15 s; primary
+  # ⚠ Single backend until the second RTX 2000 lands (Prime, 2026-09-25): if
-  # HOST DOWN (no ARP) → ~18.7 s on EVERY call (no cooldown kicked in). Slow,
+  # esh-ml1, esh-pve or the ESH mesh route is down, fleet embeddings are down.
-  # not broken. ⚠ Never add a deployment here that serves a DIFFERENT embedding
+  # ⚠ Never point this name at a DIFFERENT embedding model — vectors are
-  # model — vectors are model-specific and a mixed group corrupts indexes.
+  # model-specific. Engine bake-off: docs/pfi/embed-rerank-tei-vs-vllm-bakeoff.md.
-  # esh-ml1: stacks/embed-rerank, playbooks/esh-ml1-lxc.yaml.
-  - model_name: qwen3-embedding
-    litellm_params:
-      model: hosted_vllm/Qwen/Qwen3-Embedding-0.6B
-      api_base: http://10.251.50.54:8001/v1
-      api_key: os.environ/VLLM_API_KEY
-      order: 1
-    model_info:
-      mode: embedding
   - model_name: qwen3-embedding
     litellm_params:
       model: hosted_vllm/Qwen/Qwen3-Embedding-0.6B
       api_base: http://10.0.50.80:8001/v1
       api_key: os.environ/VLLM_API_KEY
-      order: 2
     model_info:
       mode: embedding
 
@@ -508,23 +498,17 @@ model_list:
     model_info:
       mode: chat
   # reranker → generic capability name for rerank (bge-reranker-v2-m3 since the
-  # R43 cutover). fv-ml1 order 1, esh-ml1 order 2 — same failover shape as
+  # R43 cutover). ONE backend: TEI on esh-ml1 (fv-ml1's vLLM seat retired
-  # qwen3-embedding above. Parity measured 2026-09-24: |score| FV-vs-ESH max
+  # 2026-09-25). ⚠ TEI's /rerank takes `texts`, not `documents`: this MUST use the
-  # 0.000145 vs FV-vs-FV floor 0.000181, identical ranking over 11 documents.
+  # `huggingface/` provider. `hosted_vllm/` gets a 422 "missing field texts".
+  # api_base has NO /v1. api_key is a placeholder; TEI runs without auth.
+  # Parity vs the retired vLLM seat: top-1/top-3 identical (129/130 top-1 over
+  # two runs); scores move up to 0.019, reshuffling only near-zero tail docs.
   - model_name: reranker
     litellm_params:
-      model: hosted_vllm/BAAI/bge-reranker-v2-m3
+      model: huggingface/BAAI/bge-reranker-v2-m3
-      api_base: http://10.251.50.54:8013/v1
+      api_base: http://10.0.50.80:8013
-      api_key: os.environ/VLLM_API_KEY
+      api_key: "none"
-      order: 1
-    model_info:
-      mode: rerank
-  - model_name: reranker
-    litellm_params:
-      model: hosted_vllm/BAAI/bge-reranker-v2-m3
-      api_base: http://10.0.50.80:8013/v1
-      api_key: os.environ/VLLM_API_KEY
-      order: 2
     model_info:
       mode: rerank
 

stacks/tei-bakeoff/compose.yaml

@@ -1,81 +0,0 @@
-# tei-bakeoff — Hugging Face Text Embeddings Inference (TEI) serving the SAME two
-# models as stacks/embed-rerank (vLLM), side by side on esh-ml1, so the two
-# engines can be compared on identical hardware. Prime, 2026-09-25: "run the
-# TEI bake-off". Not wired into the gateway. Temporary: either this becomes the
-# embed-rerank stack or it is torn down.
-#
-#   tei-embed    Qwen/Qwen3-Embedding-0.6B  → /v1/embeddings, /embed   :8081
-#   tei-rerank   BAAI/bge-reranker-v2-m3    → /rerank                  :8083
-#
-# 89-* = the Ada Lovelace (sm_89) build. Pinned to an exact release.
-# TEI on CUDA offers float16/float32 only (no bfloat16), while vLLM serves
-# Qwen3-Embedding in bf16 — the parity measurement is what decides whether
-# that matters.
-# (--max-batch-tokens 32768 was tried on tei-embed: whole-novel time unchanged,
-# 39.2–40.4 s vs 39.9–40.3 s, so it stays at the default.)
-# --max-client-batch-size 128: the default is 32; vLLM has no such cap and the
-# bake-off sends 64 per request.
-# Separate HF cache from vLLM's, so neither engine can disturb the other's files.
-
-name: tei-bakeoff
-
-services:
-  tei-embed:
-    image: ghcr.io/huggingface/text-embeddings-inference:89-1.9.4
-    container_name: tei-embed
-    restart: unless-stopped
-    ports:
-      - "8081:80"
-    volumes:
-      - /opt/aimodels/tei-cache:/data
-    command:
-      - --model-id
-      - Qwen/Qwen3-Embedding-0.6B
-      - --served-model-name
-      - Qwen/Qwen3-Embedding-0.6B
-      - --dtype
-      - float16
-      - --max-client-batch-size
-      - "128"
-      # FAIL-CLOSED on over-length input (Dvalin review 2026-09-25; measured:
-      # TEI's default silently cut a ~40k-token input to 16,384 and returned
-      # 200, where vLLM returns 400). Truncation off requires max-batch-tokens
-      # >= the model's max input (Qwen3-Embedding: 32,768) or TEI refuses to start.
-      - --auto-truncate
-      - "false"
-      - --max-batch-tokens
-      - "32768"
-    deploy:
-      resources:
-        reservations:
-          devices:
-            - driver: nvidia
-              device_ids: ["0"]
-              capabilities: [gpu]
-
-  tei-rerank:
-    image: ghcr.io/huggingface/text-embeddings-inference:89-1.9.4
-    container_name: tei-rerank
-    restart: unless-stopped
-    ports:
-      - "8083:80"
-    volumes:
-      - /opt/aimodels/tei-cache:/data
-    command:
-      - --model-id
-      - BAAI/bge-reranker-v2-m3
-      - --dtype
-      - float16
-      - --max-client-batch-size
-      - "128"
-      # Fail-closed, as tei-embed. bge-reranker-v2-m3 max input (8,192) fits the
-      # default max-batch-tokens (16,384).
-      - --auto-truncate
-      - "false"
-    deploy:
-      resources:
-        reservations:
-          devices:
-            - driver: nvidia
-              device_ids: ["0"]
-              capabilities: [gpu]

stacks/vllm/.env.example

@@ -12,23 +12,15 @@
 VLLM_VERSION=v0.24.0
 
 # Host ports (container always listens on 8000 internally)
-EMBED_PORT=8001
+# (EMBED_PORT 8001 / RERANK_PORT 8013 retired 2026-09-25 with their seats —
-# 8013 — the reranker moved here 2026-08-20 when bge-v2-m3 (the R43 winner, which
+# embedding + reranking moved to TEI on esh-ml1, stacks/embed-rerank.)
-# had been running as a throwaway `docker run` on this port) was promoted into
-# this stack and the Qwen incumbent on :8002 was retired.
-RERANK_PORT=8013
 REWARD_PORT=8003
 
 # GPU assignment — all services share this GPU
 # (ana-ml2 has 0 and 1; default 1 keeps 0 free for heavy LLM work in llama-swap)
 GPU_ID=1
 
-# Models — reference by full repo name in API requests
+# Models
-EMBED_MODEL=Qwen/Qwen3-Embedding-0.6B
-# bge-reranker-v2-m3 — the R43 bake-off winner, replacing Qwen3-Reranker-0.6B
-# (measured HARMING 80/90 fleet queries). Multilingual cross-encoder; needs no
-# --hf-overrides, unlike the Qwen reranker it displaced.
-RERANK_MODEL=BAAI/bge-reranker-v2-m3
 # Skywork is a local-path AWQ output, not from HF Hub. Bind-mounted into the
 # reward container at /local-models — see compose.yaml. No env var here for
 # the model path itself since it's hard-coded in the compose command.
@@ -62,16 +54,12 @@ RERANK_MODEL=BAAI/bge-reranker-v2-m3
 # each at 0.05 (mostly util-reservation waste); 0.03 (~3.6 GB) fits weights +
 # CUDA context with room, freeing ~4 GB back to granite. Recreate them ONE AT A
 # TIME — concurrent recreate races the memory-profiling assertion.
-EMBED_GPU_MEM_UTIL=0.03
-RERANK_GPU_MEM_UTIL=0.03
 REWARD_GPU_MEM_UTIL=0.10
 
 # Context length caps — lower these if VRAM is tight.
 # Qwen3-Embedding supports up to 32k; reranker up to 32k.
 # Skywork capped at 16k server-side as defense-in-depth; JudgeClient also
 # enforces the cap at dispatch time per spec.
-EMBED_MAX_MODEL_LEN=8192
-RERANK_MAX_MODEL_LEN=8192
 REWARD_MAX_MODEL_LEN=16384
 
 # Optional API key — leave blank for no auth (fine on the internal network).

stacks/vllm/README.md

@@ -1,5 +1,11 @@
 # vllm
 
+> ⚠ **2026-09-25: embedding + reranking LEFT this stack.** `vllm-embed` and
+> `vllm-rerank-a3` were retired; the fleet's embed/rerank now runs on **TEI on
+> esh-ml1** (`stacks/embed-rerank`), and TEI is the fleet engine for those from
+> now on (Prime). What remains here is `vllm-reward` and `vllm-coder` on fv-ml1.
+> The history below predates that.
+
 Multi-service vLLM stack on ana-ml2. Started as Qwen3 embedding + rerank
 (replacing the unmaintained Infinity stack); generalized to host any vLLM
 model on the box, currently three services:

stacks/vllm/compose.yaml

@@ -1,162 +1,27 @@
-# vLLM — Qwen3 Embedding + Reranker + Skywork Reward-V2 classifier.
+# vLLM — utility seats on fv-ml1: Skywork Reward-V2 classifier + the coder FIM seat.
 #
 # Originally created to replace the unmaintained Infinity stack (embed +
 # rerank); generalized 2026-05-13 to host any vLLM-served model on fv-ml1,
 # starting with the Skywork-Reward-V2-Llama-3.1-8B reward classifier
 # (AWQ-quantized locally, served from /tank/aimodels/llm/).
 #
-# vLLM runs one model per process, so this stack brings up three containers
+# ⚠ Embedding + reranking LEFT this stack 2026-09-25 (Prime): they now run on TEI
-# sharing a single GPU:
+# on esh-ml1 (stacks/embed-rerank), and TEI is the fleet's embed/rerank engine
-#
+# from now on. Do not re-add them here.
-#   vllm-embed   — Qwen3-Embedding served as an OpenAI /v1/embeddings server
-#   vllm-rerank  — Qwen3-Reranker served as a /rerank + /score server
-#   vllm-reward  — Skywork-Reward-V2-Llama-3.1-8B-AWQ served as a /classify scorer
-#
-# The reranker is a causal-LM checkpoint; --hf-overrides re-maps it to
-# Qwen3ForSequenceClassification so vLLM's reranking endpoints work and the
-# model only emits two class logits (no/yes) instead of the full 151k vocab.
 #
 # All tunables live in .env — edit that, not this file.
 #
-# Pre-download models to avoid first-run delay:
-#   scripts/elway fv-ml1 --playbook playbooks/pull-hf-repo.yaml \
-#       --var hf_repo=Qwen/Qwen3-Embedding-0.6B
-#   scripts/elway fv-ml1 --playbook playbooks/pull-hf-repo.yaml \
-#       --var hf_repo=Qwen/Qwen3-Reranker-0.6B
-#
 # Skywork-Reward-V2-Llama-3.1-8B-AWQ is a locally-quantized model — lives at
 # /tank/aimodels/llm/Skywork-Reward-V2-Llama-3.1-8B-AWQ on fv-ml1 and is
 # bind-mounted into the reward service at /local-models. Not from HF Hub.
 
 services:
-  vllm-embed:
+  # vllm-embed (Qwen3-Embedding-0.6B, :8001) and vllm-rerank-a3
-    image: vllm/vllm-openai:${VLLM_VERSION}
+  # (bge-reranker-v2-m3, :8013) were RETIRED 2026-09-25 (Prime): embedding and
-    container_name: vllm-embed
+  # reranking moved to TEI on esh-ml1 (stacks/embed-rerank), and TEI is now the
-    restart: unless-stopped
+  # fleet's embed/rerank engine. The gateway names `qwen3-embedding`, `reranker`
-    ipc: host
+  # and `reranker-a3-bge-v2-m3` did not change. Their definitions are in git
-    ports:
+  # history before this commit if a rollback is ever needed.
-      - "${EMBED_PORT}:8000"
-    volumes:
-      - /tank/aimodels/huggingface:/hfcache
-    environment:
-      - HF_HOME=/hfcache
-      - HF_HUB_CACHE=/hfcache/hub
-      - HUGGING_FACE_HUB_TOKEN=${HF_TOKEN:-}
-      - VLLM_API_KEY=${API_KEY:-}
-    command:
-      - ${EMBED_MODEL}
-      - --served-model-name
-      - ${EMBED_MODEL}
-      - --runner
-      - pooling
-      - --host
-      - 0.0.0.0
-      - --port
-      - "8000"
-      - --gpu-memory-utilization
-      - ${EMBED_GPU_MEM_UTIL}
-      - --max-model-len
-      - ${EMBED_MAX_MODEL_LEN}
-      - --dtype
-      - auto
-    deploy:
-      resources:
-        reservations:
-          devices:
-            - driver: nvidia
-              device_ids:
-                - "${GPU_ID}"
-              capabilities:
-                - gpu
-    healthcheck:
-      test: ["CMD", "curl", "-f", "http://localhost:8000/health"]
-      interval: 30s
-      timeout: 10s
-      retries: 3
-      start_period: 180s
-    networks:
-      - tnet
-    labels:
-      - homepage.group=AI - Eval & Retrieval
-      - homepage.name=vLLM Embed (Qwen3)
-      - homepage.icon=mdi-vector-arrange-below
-      - homepage.description=Qwen3 Embedding via vLLM (fv-ml1)
-      - homepage.href=http://10.251.50.54:${EMBED_PORT}/docs
-
-  # THE fleet reranker. Backs the LiteLLM `reranker` alias, which is what every
-  # consumer should name — never the model, never a bake-off arm name.
-  #
-  # It won the Brokkr R43 bake-off (docs/pfi/reranker-selection-ledger.md) and
-  # replaced Qwen3-Reranker-0.6B, which was measured HARMING 80/90 fleet queries
-  # (no-reranker beat it 89/90 vs 56/90). The R42 v13 acceptance gate went
-  # 56/90 -> 90/90 on the cutover, its first-ever PASS.
-  #
-  # Promoted from a throwaway `docker run` to this service 2026-08-20 (the
-  # ledger's own open follow-up). It carried the bake-off's arm name from the
-  # start and KEEPS it: the ledger, persistent-memory and the R43 record all say
-  # `vllm-rerank-a3`, and renaming for tidiness would orphan every one of those
-  # references. The name carries its provenance.
-  #
-  # Retired alongside this promotion: `vllm-rerank` (Qwen3-Reranker-0.6B, :8002 —
-  # the rollback path, kept warm 13 days) and `vllm-rerank-a4`
-  # (gte-reranker-modernbert, :8014 — a documented throughput fallback that was
-  # never given a gateway alias, so it was unreachable the whole time).
-  vllm-rerank-a3:
-    image: vllm/vllm-openai:${VLLM_VERSION}
-    container_name: vllm-rerank-a3
-    restart: unless-stopped
-    ipc: host
-    ports:
-      - "${RERANK_PORT}:8000"
-    volumes:
-      - /tank/aimodels/huggingface:/hfcache
-    environment:
-      - HF_HOME=/hfcache
-      - HF_HUB_CACHE=/hfcache/hub
-      - HUGGING_FACE_HUB_TOKEN=${HF_TOKEN:-}
-      - VLLM_API_KEY=${API_KEY:-}
-    command:
-      - ${RERANK_MODEL}
-      - --served-model-name
-      - ${RERANK_MODEL}
-      - --runner
-      - pooling
-      # No --hf-overrides here. The Qwen reranker needed one to be coerced into a
-      # sequence-classification head; bge-reranker-v2-m3 is natively a
-      # cross-encoder and vLLM resolves it directly.
-      - --host
-      - 0.0.0.0
-      - --port
-      - "8000"
-      - --gpu-memory-utilization
-      - ${RERANK_GPU_MEM_UTIL}
-      - --max-model-len
-      - ${RERANK_MAX_MODEL_LEN}
-      - --dtype
-      - auto
-    deploy:
-      resources:
-        reservations:
-          devices:
-            - driver: nvidia
-              device_ids:
-                - "${GPU_ID}"
-              capabilities:
-                - gpu
-    healthcheck:
-      test: ["CMD", "curl", "-f", "http://localhost:8000/health"]
-      interval: 30s
-      timeout: 10s
-      retries: 3
-      start_period: 180s
-    networks:
-      - tnet
-    labels:
-      - homepage.group=AI - Eval & Retrieval
-      - homepage.name=vLLM Rerank (bge-v2-m3)
-      - homepage.icon=mdi-sort-variant
-      - homepage.description=BAAI bge-reranker-v2-m3 — the fleet reranker, backs the `reranker` alias (fv-ml1)
-      - homepage.href=http://10.251.50.54:${RERANK_PORT}/docs
 
   vllm-reward:
     image: vllm/vllm-openai:${VLLM_VERSION}