You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
I can reproduce the error with cuda and llvm backend. For llvm, I get
File "/home/masa/projects/dev/tvm/src/target/llvm/codegen_llvm.cc", line 776
TVMError:
---------------------------------------------------------------
An internal invariant was violated during the execution of TVM.
Please read TVM's error reporting guidelines.
More details can be found here: https://discuss.tvm.ai/t/error-reporting/7793.
---------------------------------------------------------------
Check failed: f == false: Cannot find intrinsic declaration, possible type mismatch: llvm.exp
@naokishibuya If I remove quant/dequant, it works. So I think it is the problem of sigmoid applied to uint8 type. Are you sure you want to run sigmoid on quantized input? I'm not sure how sigmoid is supposed to work on uint8.
@masahi that's a great findings! The actual model I use has sigmoid at the end of the network to make the outputs in [0, 1]. So, I could call dequant before the sigmoid to avoid this exception with little increase in the latency. Thanks again.
Hello,
I encountered an exception from relay with a PyTorch model that has
nn.Sigmoid
.To reproduce the error, the script below can be used.
nn.Sigmoid
.relay.build
throws an exceptionTVMError: Unresolved call Op(tir.exp)
.target='cuda'
andtarget='llvm'
.nn.Sigmoid
withnn.Linear
, it works.The output from running the script is as follows:
The text was updated successfully, but these errors were encountered: