glm53-flash-fp4-local-2x: GB10-safe limits — card's 500K ctx + GMU 0.87 + 4 seqs stalled both Sparks (unified-memory exhaustion, forum 386057). Cut to GMU 0.75 + 32768 ctx + 2 seqs (bench-ample, host headroom)

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

@@ -24,6 +24,15 @@ parent_model = "zai-org/GLM-5.3-Flash"
 port = 30000
 required_nodes = 2
 tensor_parallel_size = 2
+# GB10 adaptation of the card's DGX-Spark-x2 block: the card ships
+# --max-model-len 500000 + --gpu-memory-utilization 0.87 + --max-num-seqs 4.
+# On GB10 (unified memory, not cgroup-contained — forum 386057) that first
+# attempt STALLED both nodes: 83 GB weights/rank + the VL tower + b12x + CUDA
+# graphs + a 500K-token KV reservation blew past the 119 GB host pool and
+# sshd could no longer fork (nodes ping but refuse SSH). Cut to GMU 0.75 +
+# 32768 ctx + 2 seqs — ample for tool-eval-bench scenarios, leaves host
+# headroom. Recovery from a stall is an HA plug cycle of switch.dgx3/dgx4
+# ONLY (never the shared fabric switch).
 args = [
     "--served-model-name", "glm53-fp4-local",
     "--dtype", "bfloat16",
@@ -38,13 +47,13 @@ args = [
     "--linear-backend", "b12x",
     "--no-enable-flashinfer-autotune",
     "--load-format", "b12x",
-    "--max-model-len", "500000",
-    "--max-num-seqs", "4",
+    "--max-model-len", "32768",
+    "--max-num-seqs", "2",
     "--max-num-batched-tokens", "4096",
     "--reasoning-parser", "glm45",
     "--tool-call-parser", "glm47",
     "--enable-auto-tool-choice",
-    "--gpu-memory-utilization", "0.87",
+    "--gpu-memory-utilization", "0.75",
     "--speculative-config", """
 '{"method":"mtp","num_speculative_tokens":5,"moe_backend":"humming","attention_backend":"B12X"}'""",
 ]