[Bugfix] Fix inverted PP-disable condition for diffusion LLM inference (#27700)

Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-24 20:18:00 -07:00
parent 8b7a1e908a
commit c268a7edf5
1 changed files with 1 additions and 1 deletions
@@ -6216,7 +6216,7 @@ class ServerArgs:
                )
                self.enable_lmcache = False

-        if not self.pp_size > 1:
+        if self.pp_size > 1:
            logger.warning(
                "Pipeline parallelism is disabled because of using diffusion LLM inference"
            )