update

Author: jenniew

torchchat/generate.py

@@ -1215,7 +1215,6 @@ def callback(x, *, done_generating=False):
                     print(prof.key_averages().table(sort_by="self_cuda_time_total"))
                 else:
                     print(prof.key_averages().table(sort_by="self_xpu_time_total"))
-                    torch.save(prof.key_averages().table(sort_by="self_xpu_time_total"), f"./{self.profile}.pt")
                 prof.export_chrome_trace(f"{self.profile}.json")
 
             if start_pos >= max_seq_length: