LiangHao151941 commented on issue #4828: [QNN][TFLite] TFLite rounding mode support URL: https://github.com/apache/incubator-tvm/pull/4828#issuecomment-596081314 > Do you think it will be good if you send a separate PR for pooling op? I think it is more like a bug of pooling op integer implementation. It will also make this PR just take care of TFLite rounding. I'm fine with both choices. The pooling implementation doesn't affect any other test except for this bit-exact computation. It can be regarded as bug or feature to me : ) (as np.mean choose FLOOR implementation for integer inputs). @FrozenGene @tqchen > I think you are confusing the GPU container with GPU target. The tests are still running on CPU. > > * You might have done this already. But have you run mobilenetv2 locally? Yes, and it passed smoothly. > * If it passes locally, then lets check the LLVM version. And re-run with whatever container is running with. > * You can also try change the target from `llvm` to `llvm -mcpu=core-avx2' in TFLite tests. There is a LLVM bug which might be causing this - https://discuss.tvm.ai/t/segfault-in-llvm/3567 I have LLVM 9.0.1, compiled from source code. In my local env, `_test_forward_elemwise(partial(_test_add, fused_activation_function="RELU6"))` is failing while not in ci test. I'm not sure about the llvm version used in the ci.
---------------------------------------------------------------- This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to go to the specific comment. For queries about this service, please contact Infrastructure at: [email protected] With regards, Apache Git Services
