A high-throughput and memory-efficient inference and serving engine for LLMs
Mirrored from https://github.com/tduncan-lum/Nvidia-Optimization-Stack---VLLM.git
Synced Nov 17, 00:30 UTC
[Minor] Fix small typo in llama.py: QKVParallelLinear -> QuantizationConfig (#4991)
Philipp Moritz committed
May 22, 2024 at 15:26 UTC
a36de682d4283c60777bc3022ed3ce71cd90b904
1 file changed
+1
-1
vllm/model_executor/models/llama.py
+1
-1
@@ -57,7 +57,7 @@ class LlamaMLP(nn.Module):
57
hidden_size: int,
58
intermediate_size: int,
59
hidden_act: str,
60
- quant_config: Optional[QKVParallelLinear] = None,
60
+ quant_config: Optional[QuantizationConfig] = None,
61
bias: bool = False,
62
) -> None:
63
super().__init__()