[Frontend] Using matryoshka_dimensions control the allowed output dimensions. (#16970)

2025-04-24 22:06:28 +08:00
parent b724afe343
commit 67309a1cb5
8 changed files with 172 additions and 76 deletions
--- a/vllm/config.py
+++ b/vllm/config.py
@@ -1248,6 +1248,10 @@ class ModelConfig:
        return (hasattr(self.hf_config, "matryoshka_dimensions")
                or getattr(self.hf_config, "is_matryoshka", False))

+    @property
+    def matryoshka_dimensions(self):
+        return getattr(self.hf_config, "matryoshka_dimensions", None)
+

 BlockSize = Literal[1, 8, 16, 32, 64, 128]
 CacheDType = Literal["auto", "fp8", "fp8_e4m3", "fp8_e5m2"]