add gh issue to comment

microsoft · Dec 31, 2024 · 307c960 · 307c960
1 parent 4218e36
commit 307c960
Showing 1 changed file with 2 additions and 1 deletion.
diff --git a/olive/passes/pytorch/gptq.py b/olive/passes/pytorch/gptq.py
@@ -160,7 +160,8 @@ def _run_for_config(
         quantized_model: BaseGPTQForCausalLM = model_class(pytorch_model, False, quantize_config)
 
         # explicitly move quantized model to CUDA device to avoid the "Expected all tensors to be
-        # on the same device" error in auto-gptq
+        # on the same device" error in auto-gptq.
+        # see https://github.com/AutoGPTQ/AutoGPTQ/issues/729 
         quantized_model.to("cuda")
 
         fields_to_set = {