feat: Mount the KV scale sidecar from any host path

The container read the sidecar only inside the MODEL_DIR mount, so a
scale file in another folder needed a manual -v and a container path.

Bind-mount the file named by SCALES to /opt/vllm/qsa_kv_scales.json, and
pass that fixed path to the engine. The default stays
$MODEL_DIR/qsa_kv_scales.json, so the shipped setup does not change. Add
a commented SCALES entry to .env.example.

Co-Authored-By: Hinata <hinata@idihore.id>
Signed-off-by: MOVZX <movzx@yahoo.com>

docker-compose.yml

@@ -28,7 +28,7 @@ services:
     environment:
       MODEL_NAME: ${MODEL_NAME:-Hinata}
       PORT: 8000
-      SCALES: ${SCALES:-}
+      SCALES: /opt/vllm/qsa_kv_scales.json
       VLLM_API_KEY: ${VLLM_API_KEY:-}
       PLE_HOME: ${PLE_HOME:-0}
       CUDA_VISIBLE_DEVICES: ${CUDA_VISIBLE_DEVICES:-0,1,2,3}
@@ -45,6 +45,7 @@ services:
       - "${MODEL_DIR:?Set MODEL_DIR in .env}:${MODEL_MOUNT_PATH:-/models/Qwen3.8-Flash-Next}:ro"
       - ${ABLITERATION_DIR:-./abliteration}:/opt/qwen38/abliteration:ro
       - ${CACHE_HOST_DIR:-./.vllm-cache}:/cache
+      - ${SCALES:-${MODEL_DIR}/qsa_kv_scales.json}:/opt/vllm/qsa_kv_scales.json:ro
       - ./start.sh:/opt/vllm/start.sh:ro
     restart: unless-stopped
     stop_grace_period: 20s