Fix cuda graph max bs capture upper bound (#21005)

2026-03-31 15:20:56 -07:00
parent 3c91ebdf55
commit 9191b02eda
1 changed files with 3 additions and 0 deletions
@@ -1352,6 +1352,9 @@ class ServerArgs:

        capture_bs = [bs for bs in capture_bs if bs <= self.cuda_graph_max_bs]

+        if self.cuda_graph_max_bs not in capture_bs:
+            capture_bs.append(self.cuda_graph_max_bs)
+
        return capture_bs

    def _generate_cpu_graph_batch_sizes(self):