-
Notifications
You must be signed in to change notification settings - Fork 3.7k
Closed
Labels
needs-triagePRs or issues that need to be investigated by maintainers to find the right assignees to address itPRs or issues that need to be investigated by maintainers to find the right assignees to address ittype: bug
Description
Actual behavior
Traceback (most recent call last):
File "demo.py", line 25, in <module>
vm = relax.VirtualMachine(ex, tvm.cpu())
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/software/tvm/python/tvm/runtime/relax_vm.py", line 97, in __init__
self._setup_device(device, memory_cfg)
File "/software/tvm/python/tvm/runtime/relax_vm.py", line 133, in _setup_device
self.module["vm_initialization"](*init_args)
File "/software/tvm/python/tvm/_ffi/_ctypes/packed_func.py", line 239, in __call__
raise_last_ffi_error()
File "/software/tvm/python/tvm/_ffi/base.py", line 481, in raise_last_ffi_error
raise py_err
tvm.error.InternalError: Traceback (most recent call last):
3: _ZN3tvm7runtime13PackedFuncObj9ExtractorINS0_16PackedFuncSubObjIZNS0_8relax_vm18VirtualMachineImpl
2: tvm::runtime::relax_vm::VirtualMachineImpl::_Init(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*)
1: tvm::runtime::relax_vm::VirtualMachineImpl::Init(std::vector<DLDevice, std::allocator<DLDevice> > const&, std::vector<tvm::runtime::memory::AllocatorType, std::allocator<tvm::runtime::memory::AllocatorType> > const&)
0: tvm::runtime::relax_vm::VirtualMachineImpl::InitFuncPool()
File "/software/tvm/src/runtime/relax_vm/vm.cc", line 705
InternalError: Check failed: (func.defined()) is false: Error: Cannot find PackedFunc tir_zeros in either Relax VM kernel library, or in TVM runtime PackedFunc registry, or in global Relax functions of the VM executable
Environment
- TVM: 0.17.dev0
- OS: Ubuntu20.04
Steps to reproduce
import tvm
from tvm import relax
from tvm.script import ir as I
from tvm.script import tir as T
from tvm.script import relax as R
@I.ir_module
class Module:
I.module_attrs({"system_lib_prefix": "hello_"})
@T.prim_func
def tir_zeros(x: T.Buffer((2,), "float32")):
x[0] = T.float32(0)
@R.function
def main() -> R.Tensor((2,), dtype="float32"):
cls = Module
gv0 = R.call_tir(cls.tir_zeros, R.tuple(), out_sinfo=R.Tensor((2,), dtype="float32"))
return gv0
m = Module
m.show()
ex = relax.build(m, target='llvm')
vm = relax.VirtualMachine(ex, tvm.cpu())
Metadata
Metadata
Assignees
Labels
needs-triagePRs or issues that need to be investigated by maintainers to find the right assignees to address itPRs or issues that need to be investigated by maintainers to find the right assignees to address ittype: bug