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 eafa8dc commit 2b30afaCopy full SHA for 2b30afa
vllm/config/__init__.py
@@ -1426,6 +1426,11 @@ def get_head_size(self) -> int:
1426
if getattr(self.hf_text_config, "head_dim", None) is not None:
1427
return self.hf_text_config.head_dim
1428
1429
+ # NOTE: Some models (such as PLaMo2.1) use `hidden_size_per_head`
1430
+ if getattr(self.hf_text_config, "hidden_size_per_head",
1431
+ None) is not None:
1432
+ return self.hf_text_config.hidden_size_per_head
1433
+
1434
# FIXME(woosuk): This may not be true for all models.
1435
return (self.hf_text_config.hidden_size //
1436
self.hf_text_config.num_attention_heads)
0 commit comments