Hello I’m trying to implement vit quantzaiton.
My input tensor type of relay.qnn.op.batch_matmul is int16.
When i passed my x, y to relay.qnn.op.batch_matmul, i got some errors like below.
Is there any int16 batch_matmul function in tvm relay?
matmul = relay.qnn.op.batch_matmul(x, y,
x_zero_point,
y_zero_point,
x_scale,
y_scale,
out_dtype="int32")
Traceback (most recent call last):
File "evaluate_val_accuracy.py", line 201, in <module>
main(args)
File "evaluate_val_accuracy.py", line 106, in main
func, params = build_model.get_workload(name=name,
File "/home/gihkim/workspace/mr-branch/TVM_benchmark/models/build_model.py", line 70, in get_workload
return create_workload(net, QuantizeInitializer())
File "/home/gihkim/workspace/mr-branch/TVM_benchmark/models/utils.py", line 163, in create_workload
mod = relay.transform.InferType()(mod)
File "/home/gihkim/workspace/tvm/python/tvm/ir/transform.py", line 161, in __call__
return _ffi_transform_api.RunPass(self, mod)
File "/home/gihkim/workspace/tvm/python/tvm/_ffi/_ctypes/packed_func.py", line 237, in __call__
raise get_last_ffi_error()
tvm._ffi.base.TVMError: Traceback (most recent call last):
7: TVMFuncCall
6: tvm::runtime::PackedFuncObj::Extractor<tvm::runtime::PackedFuncSubObj<tvm::runtime::TypedPackedFunc<tvm::IRModule (tvm::transform::Pass, tvm::IRModule)>::AssignTypedLambda<tvm::transform::{lambda(tvm::transform::Pass, tvm::IRModule)#7}>(tvm::transform::{lambda(tvm::transform::Pass, tvm::IRModule)#7}, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> >)::{lambda(tvm::runtime::TVMArgs const&, tvm::runtime::TVMRetValue*)#1}> >::Call(tvm::runtime::PackedFuncObj const*, tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*)
5: tvm::transform::Pass::operator()(tvm::IRModule) const
4: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
3: tvm::transform::ModulePassNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
2: tvm::runtime::PackedFuncObj::Extractor<tvm::runtime::PackedFuncSubObj<tvm::runtime::TypedPackedFunc<tvm::IRModule (tvm::IRModule, tvm::transform::PassContext)>::AssignTypedLambda<tvm::relay::transform::InferType()::{lambda(tvm::IRModule, tvm::transform::PassContext const&)#1}>(tvm::relay::transform::InferType()::{lambda(tvm::IRModule, tvm::transform::PassContext const&)#1})::{lambda(tvm::runtime::TVMArgs const&, tvm::runtime::TVMRetValue*)#1}> >::Call(tvm::runtime::PackedFuncObj const*, tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*)
1: tvm::relay::TypeInferencer::Infer(tvm::GlobalVar, tvm::relay::Function)
0: tvm::relay::TypeSolver::Solve() [clone .cold]
10: TVMFuncCall
9: tvm::runtime::PackedFuncObj::Extractor<tvm::runtime::PackedFuncSubObj<tvm::runtime::TypedPackedFunc<tvm::IRModule (tvm::transform::Pass, tvm::IRModule)>::AssignTypedLambda<tvm::transform::{lambda(tvm::transform::Pass, tvm::IRModule)#7}>(tvm::transform::{lambda(tvm::transform::Pass, tvm::IRModule)#7}, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> >)::{lambda(tvm::runtime::TVMArgs const&, tvm::runtime::TVMRetValue*)#1}> >::Call(tvm::runtime::PackedFuncObj const*, tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*)
8: tvm::transform::Pass::operator()(tvm::IRModule) const
7: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
6: tvm::transform::ModulePassNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
5: tvm::runtime::PackedFuncObj::Extractor<tvm::runtime::PackedFuncSubObj<tvm::runtime::TypedPackedFunc<tvm::IRModule (tvm::IRModule, tvm::transform::PassContext)>::AssignTypedLambda<tvm::relay::transform::InferType()::{lambda(tvm::IRModule, tvm::transform::PassContext const&)#1}>(tvm::relay::transform::InferType()::{lambda(tvm::IRModule, tvm::transform::PassContext const&)#1})::{lambda(tvm::runtime::TVMArgs const&, tvm::runtime::TVMRetValue*)#1}> >::Call(tvm::runtime::PackedFuncObj const*, tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*)
4: tvm::relay::TypeInferencer::Infer(tvm::GlobalVar, tvm::relay::Function)
3: tvm::relay::TypeSolver::Solve()
2: _ZN3tvm7runtime13PackedFuncObj
1: tvm::runtime::TypedPackedFunc<bool (tvm::runtime::Array<tvm::Type, void> const&, int, tvm::Attrs const&, tvm::TypeReporter const&)>::AssignTypedLambda<bool (*)(tvm::runtime::Array<tvm::Type, void> const&, int, tvm::Attrs const&, tvm::TypeReporter const&)>(bool (*)(tvm::runtime::Array<tvm::Type, void> const&, int, tvm::Attrs const&, tvm::TypeReporter const&))::{lambda(tvm::runtime::TVMArgs const&, tvm::runtime::TVMRetValue*)#1}::operator()(tvm::runtime::TVMArgs const&, tvm::runtime::TVMRetValue*) const
0: tvm::relay::qnn::QnnBatchMatmulRel(tvm::runtime::Array<tvm::Type, void> const&, int, tvm::Attrs const&, tvm::TypeReporter const&)
File "/home/gihkim/workspace/tvm/src/relay/analysis/type_solver.cc", line 624
TVMError:
---------------------------------------------------------------
An error occurred during the execution of TVM.
For more information, please see: https://tvm.apache.org/docs/errors.html
---------------------------------------------------------------
Check failed: (false) is false: [15:34:29] /home/gihkim/workspace/tvm/src/relay/qnn/op/batch_matmul.cc:50:
---------------------------------------------------------------
An error occurred during the execution of TVM.
For more information, please see: https://tvm.apache.org/docs/errors.html
---------------------------------------------------------------
Check failed: (x->dtype == DataType::Int(8) || x->dtype == DataType::UInt(8)) is false: Expected quantized batch_matmul type(int8, uint8) for input but was int32