redeploy qwen3.6 27b

llamacpp/deployment-deepseek-v4-flash-0731.yaml

@@ -63,8 +63,7 @@ spec:
         hardware: high-memory
       initContainers:
       # Idempotently download the (3-part, split) GGUF into the shared models
-      # PVC on first boot. Also removes the retired Qwen3.6 GGUFs so the new
-      # 87 GiB model fits on the PVC. Downloads are atomic (→ .partial, then
+      # PVC on first boot. Downloads are atomic (→ .partial, then
       # rename) and resumable, so a failed/interrupted download is recovered
       # on the next pod start without re-fetching from scratch. A free-space
       # check fails loudly if the hostPath disk is genuinely too small (no
@@ -76,14 +75,8 @@ spec:
         args:
         - |
           set -e
-          # Reclaim space from the retired Qwen3.6 models (their Deployments
-          # are gone; the GGUFs are dead weight on the shared PVC).
-          for old in Qwen3.6-27B-UD-Q4_K_XL.gguf Qwen3.6-35B-A3B-UD-Q4_K_XL.gguf; do
-            if [ -f "/models/$old" ]; then
-              echo "Removing retired model $old ..."
-              rm -f "/models/$old"
-            fi
-          done
+          # Qwen3.6-27B is intentionally co-located on this PVC; do not remove
+          # it on DeepSeek pod restarts.
           # Skip entirely if every shard is already fully downloaded.
           if [ -s "/models/$SHARD1" ] && [ -s "/models/$SHARD2" ] && [ -s "/models/$SHARD3" ]; then
             echo "All 3 shards already present — skipping download."