We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
There was an error while loading. Please reload this page.
1 parent 7b35011 commit e41312aCopy full SHA for e41312a
vllm/transformers_utils/config.py
@@ -954,6 +954,13 @@ def try_get_generation_config(
954
revision: str | None = None,
955
config_format: str | ConfigFormat = "auto",
956
) -> GenerationConfig | None:
957
+ # GGUF files don't have generation_config.json - their config is embedded
958
+ # in the file header. Skip all filesystem lookups to avoid re-reading the
959
+ # memory-mapped file, which can hang in multi-process scenarios when the
960
+ # EngineCore process already has the file mapped.
961
+ if is_gguf(model):
962
+ return None
963
+
964
try:
965
return GenerationConfig.from_pretrained(
966
model,
0 commit comments