chore: keep models.example.toml generic; deploy.sh sync's local models.toml

Reverts the previous commit's naming of specific helexa neuron hosts
in the shipped example catalogue (`models.example.toml`) — the example
is supposed to be a generic starting point that any operator copies
and adapts, not a record of one particular fleet's layout.

- `pinned_on` in the TP example uses the placeholder
  `"your-multi-gpu-neuron"`. Other entries keep the model ids
  (since those are HuggingFace-canonical, not fleet-specific).
- New `models.toml` at repo root holds the helexa-fleet catalogue
  (beast / benjy / quadbrat). Added to `.gitignore` alongside
  `cortex.toml` — both are operator-owned, gitignored, RPM-marked
  `%config(noreplace)`, and synced by `deploy.sh`.
- `deploy.sh` now rsync's `models.toml` to `/etc/cortex/models.toml`
  on the gateway host on the same lifecycle as `cortex.toml`. Skips
  cleanly when no local file exists, so users without a catalogue
  aren't surprised by silent overwrites.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

.gitignore

@@ -4,5 +4,6 @@
 .idea/
 .vscode/
 cortex.toml
+models.toml
 doc/plan/*
 /target-cuda/

models.example.toml

@@ -20,20 +20,19 @@
 #   pinned_on          - optional whitelist of neuron names. Non-empty
 #                        narrows feasibility to just those neurons and
 #                        protects the model from LRU eviction there.
-#
-# The examples below match the canonical helexa fleet
-# (beast = 2x RTX 5090, benjy = RTX 4090, quadbrat = RTX 3060).
 
-# Tensor-parallel target — only beast has two big GPUs.
+# Tensor-parallel target — needs a neuron with at least 2 large GPUs.
+# The example pins to a specific neuron name; adjust or remove the
+# pinned_on entry for your own fleet.
 [[models]]
 id = "Qwen/Qwen3.6-27B"
 harness = "candle"
 vram_mb = 54000
 min_devices = 2
 min_device_vram_mb = 24000
-pinned_on = ["beast"]
+pinned_on = ["your-multi-gpu-neuron"]
 
-# Mid-size dense model — fits on benjy or beast.
+# Mid-size dense model — fits on any single GPU with ≥16 GB VRAM.
 [[models]]
 id = "Qwen/Qwen3-8B"
 harness = "candle"
@@ -41,7 +40,7 @@ vram_mb = 18000
 min_devices = 1
 min_device_vram_mb = 16000
 
-# Small GGUF quantised — runs on the smallest neuron (quadbrat).
+# Small GGUF quantised — runs on any small GPU.
 [[models]]
 id = "unsloth/Qwen3-0.6B-GGUF"
 harness = "candle"

script/deploy.sh

@@ -198,6 +198,25 @@ else
     echo "[${cortex_host}] failed to sync cortex.toml"
 fi
 
+# Sync models.toml on the same lifecycle as cortex.toml — operator-owned,
+# gitignored, drives /v1/models catalogue × topology resolution.
+if [[ -f "${REPO_DIR}/models.toml" ]]; then
+    if rsync \
+        --archive \
+        --compress \
+        --rsync-path 'sudo rsync' \
+        --chown root:root \
+        --chmod 644 \
+        "${REPO_DIR}/models.toml" \
+        "${cortex_host}:/etc/cortex/models.toml"; then
+        echo "[${cortex_host}] sync'd models.toml"
+    else
+        echo "[${cortex_host}] failed to sync models.toml"
+    fi
+else
+    echo "[${cortex_host}] no local models.toml — leaving /etc/cortex/models.toml untouched"
+fi
+
 ssh "${cortex_host}" sudo systemctl daemon-reload
 if ssh "${cortex_host}" systemctl is-active --quiet cortex.service; then
     echo "[${cortex_host}] cortex service is active"