Add Qwen3.5-397B INT4-AutoRound TP=4 recipe and Marlin fix

Production-tested recipe for running Qwen3.5-397B-A17B with INT4 AutoRound
quantization across 4 DGX Spark nodes using tensor parallelism.

Performance (4× DGX Spark, driver 580.126.09):
- Single user: 37 tok/s
- 4 concurrent: ~26 tok/s per user, ~103 tok/s aggregate

The Marlin TP fix resolves the MIN_THREAD_N=64 constraint that breaks
in_proj_ba layers at TP=4 (output_size=128/4=32 < 64). Solution:
ReplicatedLinear for B/A projections, applied via diff patches.

Key config:
- VLLM_MARLIN_USE_ATOMIC_ADD=1 (required for Marlin correctness)
- KV cache FP8, prefix caching enabled
- gpu_memory_utilization 0.78 (UMA safe margin)
- CUDAGraphs enabled (default, requires driver 580.x)

Note: Driver 590.x has CUDAGraph capture deadlock on GB10 unified memory.
Stay on driver 580.126.09.

mods/fix-qwen35-tp4-marlin/run.sh

@@ -0,0 +1,23 @@
+#!/bin/bash
+# Fix Marlin TP=4 constraint for Qwen3.5-397B: in_proj_ba output_size=128 / TP=4 = 32 < min_thread_n=64
+# Solution: Replace MergedColumnParallelLinear with two ReplicatedLinear for B/A projections
+# Delivery: unified diff patches (portable across vLLM versions)
+
+set -e
+MOD_DIR="$(dirname "$0")"
+MODELS_DIR="/usr/local/lib/python3.12/dist-packages/vllm/model_executor/models"
+
+echo "[fix-qwen35-tp4-marlin] Applying patches..."
+
+# Apply patches with --forward (skip if already applied)
+patch --forward --batch -p0 -d "$MODELS_DIR" < "$MOD_DIR/qwen3_next.patch" || {
+    echo "[fix-qwen35-tp4-marlin] qwen3_next.patch already applied or failed"
+}
+patch --forward --batch -p0 -d "$MODELS_DIR" < "$MOD_DIR/qwen3_5.patch" || {
+    echo "[fix-qwen35-tp4-marlin] qwen3_5.patch already applied or failed"
+}
+
+# Fix rope validation (idempotent)
+python3 "$MOD_DIR/fix_rope.py"
+
+echo "[fix-qwen35-tp4-marlin] Done."