glm53-flash-fp4-local-2x: cold_args GMU 0.60→0.72 — weights are 83 GiB/rank = 0.683 of the unified pool, 0.60 cannot fit them (negative KV); 0.72 leaves ~4 GiB KV and is colder than the 0.75 default attempt

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

@@ -66,7 +66,12 @@ cold_args = [
     "--max-model-len", "16384",
     "--max-num-seqs", "1",
     "--max-num-batched-tokens", "2048",
-    "--gpu-memory-utilization", "0.60",
+    # GMU 0.72, not lower: weights are ~83 GiB/rank (166 GB / 2) = 0.683 of
+    # the 121.63 GiB unified pool, so anything below ~0.70 cannot fit the
+    # weights at all (negative KV). 0.72 leaves ~4 GiB for KV + overhead —
+    # boot-safe for 16384 ctx / 1 seq, and colder than the 0.75 default
+    # attempt that stalled the nodes.
+    "--gpu-memory-utilization", "0.72",
 ]
 
 [env]