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 15, 19:45 UTC
[Doc] Fix small typo in Transformers fallback (#14791)
Signed-off-by: Chen Zhang <zhangch99@outlook.com>
Chen Zhang committed
Mar 14, 2025 at 11:33 UTC
60c872d4b665786ce4b4e1e9b82bacc0ca8e8cc2
1 file changed
+1
-1
docs/source/models/supported_models.md
+1
-1
@@ -101,7 +101,7 @@ class MyAttention(nn.Module):
101
102
def forward(self, hidden_states, **kwargs): # <- kwargs are required
103
...
104
- attention_interface = attention_interface = ALL_ATTENTION_FUNCTIONS[self.config._attn_implementation]
104
+ attention_interface = ALL_ATTENTION_FUNCTIONS[self.config._attn_implementation]
105
attn_output, attn_weights = attention_interface(
106
self,
107
query_states,