[Chore] Update type annotation of `input_ids` in model forward (#33063)

Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>

vllm/model_executor/models/ultravox.py

@@ -714,7 +714,7 @@ class UltravoxModel(nn.Module, SupportsMultiModal, SupportsPP, SupportsLoRA):
 
     def forward(
         self,
-        input_ids: torch.Tensor,
+        input_ids: torch.Tensor | None,
         positions: torch.Tensor,
         intermediate_tensors: torch.Tensor | None = None,
         inputs_embeds: torch.Tensor | None = None,

vllm/model_executor/models/voxtral.py

@@ -397,7 +397,7 @@ class VoxtralForConditionalGeneration(
 
     def forward(
         self,
-        input_ids: torch.Tensor,
+        input_ids: torch.Tensor | None,
         positions: torch.Tensor,
         intermediate_tensors: IntermediateTensors | None = None,
         inputs_embeds: torch.Tensor | None = None,

vllm/model_executor/models/voxtral_streaming.py

@@ -173,7 +173,7 @@ class VoxtralStreamingGeneration(VoxtralForConditionalGeneration):
 
     def forward(
         self,
-        input_ids: torch.Tensor,
+        input_ids: torch.Tensor | None,
         positions: torch.Tensor,
         intermediate_tensors: IntermediateTensors | None = None,
         inputs_embeds: torch.Tensor | None = None,

vllm/model_executor/models/zamba2.py

@@ -771,7 +771,7 @@ class Zamba2Model(nn.Module):
 
     def forward(
         self,
-        input_ids: torch.Tensor,
+        input_ids: torch.Tensor | None,
         positions: torch.Tensor,
         inputs_embeds: torch.Tensor | None = None,
     ) -> torch.Tensor | IntermediateTensors:
@@ -947,7 +947,7 @@ class Zamba2ForCausalLM(nn.Module, HasInnerState, IsHybrid, SupportsMambaPrefixC
 
     def forward(
         self,
-        input_ids: torch.Tensor,
+        input_ids: torch.Tensor | None,
         positions: torch.Tensor,
         inputs_embeds: torch.Tensor | None = None,
         **kwargs: Any,