when I Compile PyTorch Models demo in Compile PyTorch Models — tvm 0.8.dev0 documentation i set the configure below target = “opencl” target_host = “llvm” ctx = tvm.gpu(0) there occurs the error below: An internal invariant violated during the execution of TVM check failed:allow_missing ==false :device API gpu is not enabled
You need to use tvm.cl(0)
for opencl target. Or better: tvm.context(target, 0)
it solve the error but make errors below: check failed: ret ==0 ( -1 vs 0) check failed: e == CL_SUCCESS == false: OpenCL Error, code=-5: CL_OUT_OF_RESOURCES
it solve the error but make errors below: check failed: ret ==0 ( -1 vs 0) check failed: e == CL_SUCCESS == false: OpenCL Error, code=-5: CL_OUT_OF_RESOURCES