Merge branch 'main' into feat/diffusion-prefetch-protection

vllm_omni/diffusion/models/sd3/pipeline_sd3.py

@@ -402,12 +402,12 @@ class StableDiffusion3Pipeline(nn.Module, CFGParallelMixin, DiffusionPipelinePro
             truncation=True,
             add_special_tokens=True,
             return_tensors="pt",
-        ).to(self.device)
+        )
         text_input_ids = text_inputs.input_ids
         untruncated_ids = self.tokenizer_3(prompt, padding="longest", return_tensors="pt").input_ids
 
         if untruncated_ids.shape[-1] >= text_input_ids.shape[-1] and not torch.equal(text_input_ids, untruncated_ids):
-            removed_text = self.tokenizer_3.batch_decode(untruncated_ids[:, self.tokenizer_max_length - 1 : -1])
+            removed_text = self.tokenizer_3.batch_decode(untruncated_ids[:, max_sequence_length - 1 : -1])
             logger.warning(
                 "The following part of your input was truncated because `max_sequence_length` is set to "
                 f" {max_sequence_length} tokens: {removed_text}"