xinyun/vllm
1
0
Fork 0
mirror of https://git.datalinker.icu/vllm-project/vllm.git synced 2025-12-21 04:25:01 +08:00
Code Issues Packages Projects Releases Wiki Activity

[Minor] Fix small typo in llama.py: QKVParallelLinear -> QuantizationConfig (#4991)

Browse Source
This commit is contained in:
Philipp Moritz 2024-05-22 15:26:56 -07:00 committed by GitHub
parent eb6d3c264d
commit a36de682d4
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 1 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
vllm/model_executor/models/llama.py
View File

@ -57,7 +57,7 @@ class LlamaMLP(nn.Module):
hidden_size: int, hidden_size: int,
intermediate_size: int, intermediate_size: int,
hidden_act: str, hidden_act: str,
quant_config: Optional[QKVParallelLinear] = None, quant_config: Optional[QuantizationConfig] = None,
bias: bool = False, bias: bool = False,
) -> None: ) -> None:
super().__init__() super().__init__()