Allow optimistic prefill with L2 hierarchical cache and write-back policy (#33545)

Co-authored-by: cctry <cctry@meta.com>
2026-08-04 13:23:08 -07:00
parent abddb1c7e9
commit 34af3ff386
1 changed files with 8 additions and 2 deletions
@@ -8100,8 +8100,14 @@ class ServerArgs:
            if self.pp_size > 1:
                logger.warning("Optimistic prefill does not support pp_size > 1")
                self.optimistic_prefill_attempts = 0
-            elif self.enable_hierarchical_cache:
-                logger.warning("Optimistic prefill does not support hierarchical cache")
+            elif self.enable_hierarchical_cache and (
+                self.hicache_storage_backend is not None
+                or self.hicache_write_policy != "write_back"
+            ):
+                logger.warning(
+                    "Optimistic prefill only supports L2 hierarchical cache "
+                    "with write-back policy"
+                )
                self.optimistic_prefill_attempts = 0
            elif resolved_view(self).uses_mamba_radix_cache:
                logger.warning(