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, 02:15 UTC
[Docs] Update basic.md (#20846)
Lucia Fang committed
Jul 12, 2025 at 14:05 UTC
fb25e956885e464cb309b53e5e92d36a59542607
1 file changed
+2
docs/contributing/model/basic.md
+2
@@ -73,6 +73,8 @@ def forward(
73
self,
74
input_ids: torch.Tensor,
75
positions: torch.Tensor,
76
+ intermediate_tensors: Optional[IntermediateTensors] = None,
77
+ inputs_embeds: Optional[torch.Tensor] = None,
78
) -> torch.Tensor:
79
...
80
```