feat(erp-seat): NVFP4A16 quant pipeline for the Gemma-4 26B-A4B MoE ERP tune + ana-ml2 GPU1 serve stack

- services/erp-seat-quant/quant_nvfp4a16_gemma4_moe.py: linearize_moe first (playbook §3.15),
  asserts the expert Linear count, routers/vision/audio/norms/lm_head ignored, W4A16 for RP
  long-session fidelity, post-steps restore processor configs + template and reset the
  tokenizer truncation cap (§3.14); --dry-run proves targets before GPU time
- services/erp-seat-quant/run_quant_erp_v6.sh: detached container on GPU1 (vllm-llmcompressor)
- stacks/erp-seat: serve recipe copied from gemma4-charrp, true served name only, port 8021

services/erp-seat-quant/run_quant_erp_v6.sh

@@ -0,0 +1,18 @@
+#!/usr/bin/env bash
+# NVFP4A16 quant of the ERP run-6 merged model on ana-ml2 GPU1 (co-resident with the GPU1 seats;
+# CPU-resident load, per-layer onload). Detached container; watch with `docker logs -f erp-v6-quant`.
+# NOTE: no PYTORCH_CUDA_ALLOC_CONF=expandable_segments (playbook §3.10).
+set -euo pipefail
+WORK=/tank/aimodels/erp-tune-v6-quant-work
+SRC="${1:-/tank/aimodels/erp-tune-v6-bf16}"
+OUT="${2:-/tank/aimodels/erp-tune-v6-nvfp4a16}"
+MODE="${3:-full}"          # full | dry-run
+EXTRA=""; [ "$MODE" = "dry-run" ] && EXTRA="--dry-run"
+NAME=erp-v6-quant; [ "$MODE" = "dry-run" ] && NAME=erp-v6-quant-dry
+docker rm -f "$NAME" 2>/dev/null || true
+docker run -d --name "$NAME" --gpus '"device=1"' --ipc host \
+  -v /tank/aimodels:/tank/aimodels \
+  --entrypoint python3 vllm-llmcompressor:latest \
+  "$WORK/quant_nvfp4a16_gemma4_moe.py" --model "$SRC" --out "$OUT" \
+  --num-samples "${NUM_SAMPLES:-256}" --seqlen "${SEQLEN:-8192}" $EXTRA
+echo "launched $NAME: $(docker ps --filter name=$NAME --format '{{.Status}}')"