[Bugfix] Fix logic for choosing default prefix caching setting (#29393)

Signed-off-by: Thomas Parnell <tpa@zurich.ibm.com>
2025-11-25 15:05:10 +01:00
parent 51fc9e017a
commit 516c3f7847
2 changed files with 7 additions and 2 deletions
--- a/vllm/engine/arg_utils.py
+++ b/vllm/engine/arg_utils.py
@@ -880,7 +880,11 @@ class EngineArgs:
            "--num-gpu-blocks-override", **cache_kwargs["num_gpu_blocks_override"]
        )
        cache_group.add_argument(
-            "--enable-prefix-caching", **cache_kwargs["enable_prefix_caching"]
+            "--enable-prefix-caching",
+            **{
+                **cache_kwargs["enable_prefix_caching"],
+                "default": None,
+            },
        )
        cache_group.add_argument(
            "--prefix-caching-hash-algo", **cache_kwargs["prefix_caching_hash_algo"]