glm53-flash-fp4-local-2x: add cold_args (extra-safe first boot: gmu 0.60, 16384 ctx, 1 seq, 2048 batched) — used by 'serve --cold' over the default args

recipes/glm53-flash-fp4-local-2x/recipe.toml

@@ -58,6 +58,17 @@ args = [
 '{"method":"mtp","num_speculative_tokens":5,"moe_backend":"humming","attention_backend":"B12X"}'""",
 ]
 
+# `serve --cold` overlays these over `args` (by flag name) for an extra-safe
+# first boot on a memory-tight node — lower GMU + smaller KV than the default.
+# The default `args` are already the GB10-safe cut of the card; `--cold` is the
+# cautious first launch, then drop the flag once the lane is proven to boot.
+cold_args = [
+    "--max-model-len", "16384",
+    "--max-num-seqs", "1",
+    "--max-num-batched-tokens", "2048",
+    "--gpu-memory-utilization", "0.60",
+]
+
 [env]
 # b12x MoE/FP4 path (card "both nodes" block)
 CUTE_DSL_ARCH = "sm_121a"