We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
There was an error while loading. Please reload this page.
1 parent e77ec06 commit caf73f5Copy full SHA for caf73f5
tensorrt_llm/_torch/compilation/piecewise_optimizer.py
@@ -208,15 +208,9 @@ def __call__(self, *args):
208
runtime_input_addresses = [
209
i.data_ptr() for i in args if isinstance(i, torch.Tensor)
210
]
211
- runtime_output_addresses = [
212
- i.data_ptr() for i in output if isinstance(i, torch.Tensor)
213
- ]
214
215
assert (entry.input_addresses == runtime_input_addresses
216
), f"{entry.input_addresses} vs\n {runtime_input_addresses}"
217
- assert (
218
- entry.output_addresses == runtime_output_addresses
219
- ), f"{entry.output_addresses} vs\n {runtime_output_addresses}"
220
221
entry.cuda_graph.replay()
222
0 commit comments