Error in minimal example code for export with vulken as backend #15296
Description
🐛 Describe the bug
python code：
import torch
from torch.export import export
from executorch.exir import to_edge
from executorch.backends.vulkan.partitioner.vulkan_partitioner import VulkanPartitioner
# Start with a PyTorch model that adds two input tensors (matrices)
class Add(torch.nn.Module):
def __init__(self):
super(Add, self).__init__()
def forward(self, x: torch.Tensor, y: torch.Tensor):
return x + y
# 1. torch.export: Defines the program with the ATen operator set.
aten_dialect = export(Add(), (torch.ones(1), torch.ones(1)))
# 2. to_edge: Make optimizations for Edge devices
edge_program = to_edge(aten_dialect)
# 2.1 Lower to the Vulkan backend
edge_program = edge_program.to_backend(VulkanPartitioner())
# 3. to_executorch: Convert the graph to an ExecuTorch program
executorch_program = edge_program.to_executorch()
# 4. Save the compiled .pte program
with open("vk_add.pte", "wb") as file:
file.write(executorch_program.buffer)my error is:
---------------------------------------------------------------------------
CalledProcessError Traceback (most recent call last)
Cell In[19], line 23
21 edge_program = to_edge(aten_dialect)
22 # 2.1 Lower to the Vulkan backend
---> 23 edge_program = edge_program.to_backend(VulkanPartitioner())
25 # 3. to_executorch: Convert the graph to an ExecuTorch program
26 executorch_program = edge_program.to_executorch()
File ~/miniconda3/envs/vision/lib/python3.11/site-packages/executorch/exir/program/_program.py:114, in et_logger.<locals>.decorator.<locals>.wrapper(*args, **kwargs)
113 def wrapper(*args: Any, **kwargs: Any) -> Any:
--> 114 return func(*args, **kwargs)
File ~/miniconda3/envs/vision/lib/python3.11/site-packages/executorch/exir/program/_program.py:1672, in EdgeProgramManager.to_backend(self, partitioner)
1665 method_to_partitioner = partitioner
1667 method_to_programs_and_partitioners = MethodProgramsPartitionerSpec(
1668 self._edge_programs,
1669 method_to_partitioner,
1670 )
-> 1672 new_edge_programs = to_backend(method_to_programs_and_partitioners)
1673 config = EdgeCompileConfig(_check_ir_validity=False)
1674 epm = EdgeProgramManager(
1675 new_edge_programs,
1676 copy.deepcopy(self._config_methods),
1677 config,
1678 )
File ~/miniconda3/envs/vision/lib/python3.11/functools.py:909, in singledispatch.<locals>.wrapper(*args, **kw)
905 if not args:
906 raise TypeError(f'{funcname} requires at least '
907 '1 positional argument')
--> 909 return dispatch(args[0].__class__)(*args, **kw)
File ~/miniconda3/envs/vision/lib/python3.11/site-packages/executorch/exir/backend/backend_api.py:762, in _(method_edge_program_partitioners)
754 backend_id_to_method_submodules_map[backend_id][
755 method_name
756 ] = call_submodule_nodes
758 for (
759 backend_id,
760 method_to_submodule_nodes,
761 ) in backend_id_to_method_submodules_map.items():
--> 762 lower_all_submodules_to_backend(
763 backend_id,
764 method_to_submodule_nodes,
765 method_to_tagged_exported_program,
766 )
768 for method_name in method_to_edge_program.keys():
769 if method_name in method_to_tagged_exported_program:
File ~/miniconda3/envs/vision/lib/python3.11/site-packages/executorch/exir/backend/backend_api.py:591, in lower_all_submodules_to_backend(backend_id, method_to_submodules_nodes, method_to_tagged_edge_program)
587 if backend_id not in backend_name_to_subclass:
588 raise NotImplementedError(f"Backend {backend_id} was not found.")
590 method_to_preprocess_result: dict[str, List[PreprocessResult]] = (
--> 591 backend_name_to_subclass[backend_id].preprocess_multimethod(
592 method_to_partitioned_program, method_to_compile_specs
593 )
594 )
596 for method_name in method_to_preprocess_result.keys():
597 owning_program = method_to_tagged_edge_program[method_name]
File ~/miniconda3/envs/vision/lib/python3.11/site-packages/executorch/exir/backend/backend_details.py:129, in BackendDetails.preprocess_multimethod(cls, edge_programs, compile_specs)
125 results_for_method = []
126 for program, compile_spec_for_program in zip(
127 programs, compile_specs_for_method
128 ):
--> 129 preprocess_result = cls.preprocess(program, compile_spec_for_program)
130 results_for_method.append(preprocess_result)
132 preprocess_results[method_name] = results_for_method
File ~/miniconda3/envs/vision/lib/python3.11/site-packages/executorch/backends/vulkan/vulkan_preprocess.py:252, in preprocess(cls, program, module_compile_spec)
0 <Error retrieving source code with stack_data see ipython/ipython#13598>
File ~/miniconda3/envs/vision/lib/python3.11/site-packages/executorch/backends/vulkan/serialization/vulkan_graph_serialize.py:255, in serialize_vulkan_graph(vk_graph, const_tensors, custom_shaders)
241 raw_bytes_len = aligned_size(len(raw_bytes))
243 header: bytes = VulkanDelegateHeader(
244 flatbuffer_offset=header_len,
245 flatbuffer_size=len(flatbuffer_payload),
246 bytes_offset=header_len + flatbuffer_payload_len,
247 bytes_size=len(raw_bytes),
248 ).to_bytes()
250 return b"".join(
251 [
252 pad_to(header, header_len),
253 pad_to(flatbuffer_payload, flatbuffer_payload_len),
254 pad_to(raw_bytes, raw_bytes_len),
--> 255 ]
256 )
File ~/miniconda3/envs/vision/lib/python3.11/site-packages/executorch/backends/vulkan/serialization/vulkan_graph_serialize.py:42, in convert_to_flatbuffer(vk_graph)
40 output_path = os.path.join(d, "schema.bin")
41 with open(output_path, "rb") as output_file:
---> 42 return output_file.read()
File ~/miniconda3/envs/vision/lib/python3.11/site-packages/executorch/exir/_serialize/_flatbuffer.py:213, in _flatc_compile(output_dir, schema_path, json_path)
202 def _flatc_compile(output_dir: str, schema_path: str, json_path: str) -> None:
203 """Serializes JSON data to a binary flatbuffer file.
204
205 Args:
(...) 211 matches the schema.
212 """
--> 213 _run_flatc(
214 [
215 "--binary",
216 "-o",
217 output_dir,
218 schema_path,
219 json_path,
220 ]
221 )
File ~/miniconda3/envs/vision/lib/python3.11/site-packages/executorch/exir/_serialize/_flatbuffer.py:199, in _run_flatc(args)
197 if not flatc_path:
198 flatc_path = "flatc"
--> 199 subprocess.run([flatc_path] + list(args), check=True)
File ~/miniconda3/envs/vision/lib/python3.11/subprocess.py:571, in run(input, capture_output, timeout, check, *popenargs, **kwargs)
569 retcode = process.poll()
570 if check and retcode:
--> 571 raise CalledProcessError(retcode, process.args,
572 output=stdout, stderr=stderr)
573 return CompletedProcess(process.args, retcode, stdout, stderr)
CalledProcessError: Command '['flatc', '--binary', '-o', '/tmp/tmpjxxl4ozv', '/tmp/tmpjxxl4ozv/schema.fbs', '/tmp/tmpjxxl4ozv/schema.json']' returned non-zero exit status 1.
When I don't implement the vulkan backend, the code can run normally and the model can also be inferred normally
Versions
Collecting environment information...
PyTorch version: 2.6.0+cu126
Is debug build: False
CUDA used to build PyTorch: 12.6
ROCM used to build PyTorch: N/A
OS: Ubuntu 22.04 LTS (x86_64)
GCC version: (Ubuntu 11.2.0-19ubuntu1) 11.2.0
Clang version: Could not collect
CMake version: version 3.22.1
Libc version: glibc-2.35
Python version: 3.12.9 | packaged by Anaconda, Inc. | (main, Feb 6 2025, 18:56:27) [GCC 11.2.0] (64-bit runtime)
Python platform: Linux-5.15.0-139-generic-x86_64-with-glibc2.35
Is CUDA available: True
CUDA runtime version: 12.4.131
CUDA_MODULE_LOADING set to: LAZY
GPU models and configuration:
GPU 0: NVIDIA GeForce RTX 4090
GPU 1: NVIDIA GeForce RTX 4090
Nvidia driver version: 550.54.14
cuDNN version: Probably one of the following:
/usr/lib/x86_64-linux-gnu/libcudnn.so.9.8.0
/usr/lib/x86_64-linux-gnu/libcudnn_adv.so.9.8.0
/usr/lib/x86_64-linux-gnu/libcudnn_cnn.so.9.8.0
/usr/lib/x86_64-linux-gnu/libcudnn_engines_precompiled.so.9.8.0
/usr/lib/x86_64-linux-gnu/libcudnn_engines_runtime_compiled.so.9.8.0
/usr/lib/x86_64-linux-gnu/libcudnn_graph.so.9.8.0
/usr/lib/x86_64-linux-gnu/libcudnn_heuristic.so.9.8.0
/usr/lib/x86_64-linux-gnu/libcudnn_ops.so.9.8.0
Is XPU available: False
HIP runtime version: N/A
MIOpen runtime version: N/A
Is XNNPACK available: True
CPU:
Architecture: x86_64
CPU op-mode(s): 32-bit, 64-bit
Address sizes: 46 bits physical, 57 bits virtual
Byte Order: Little Endian
CPU(s): 64
On-line CPU(s) list: 0-63
Vendor ID: GenuineIntel
Model name: Intel(R) Xeon(R) W-3365 CPU @ 2.70GHz
CPU family: 6
Model: 106
Thread(s) per core: 2
Core(s) per socket: 32
Socket(s): 1
Stepping: 6
CPU max MHz: 4000.0000
CPU min MHz: 800.0000
BogoMIPS: 5400.00
Flags: fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush dts acpi mmx fxsr sse sse2 ss ht tm pbe syscall nx pdpe1gb rdtscp lm constant_tsc art arch_perfmon pebs bts rep_good nopl xtopology nonstop_tsc cpuid aperfmperf pni pclmulqdq dtes64 monitor ds_cpl vmx smx est tm2 ssse3 sdbg fma cx16 xtpr pdcm pcid dca sse4_1 sse4_2 x2apic movbe popcnt tsc_deadline_timer aes xsave avx f16c rdrand lahf_lm abm 3dnowprefetch cpuid_fault epb cat_l3 invpcid_single intel_ppin ssbd mba ibrs ibpb stibp ibrs_enhanced tpr_shadow vnmi flexpriority ept vpid ept_ad fsgsbase tsc_adjust bmi1 avx2 smep bmi2 erms invpcid cqm rdt_a avx512f avx512dq rdseed adx smap avx512ifma clflushopt clwb intel_pt avx512cd sha_ni avx512bw avx512vl xsaveopt xsavec xgetbv1 xsaves cqm_llc cqm_occup_llc cqm_mbm_total cqm_mbm_local split_lock_detect wbnoinvd dtherm ida arat pln pts hwp hwp_act_window hwp_epp hwp_pkg_req avx512vbmi umip pku ospke avx512_vbmi2 gfni vaes vpclmulqdq avx512_vnni avx512_bitalg tme avx512_vpopcntdq la57 rdpid fsrm md_clear pconfig flush_l1d arch_capabilities
Virtualization: VT-x
L1d cache: 1.5 MiB (32 instances)
L1i cache: 1 MiB (32 instances)
L2 cache: 40 MiB (32 instances)
L3 cache: 48 MiB (1 instance)
NUMA node(s): 1
NUMA node0 CPU(s): 0-63
Vulnerability Gather data sampling: Mitigation; Microcode
Vulnerability Itlb multihit: Not affected
Vulnerability L1tf: Not affected
Vulnerability Mds: Not affected
Vulnerability Meltdown: Not affected
Vulnerability Mmio stale data: Mitigation; Clear CPU buffers; SMT vulnerable
Vulnerability Reg file data sampling: Not affected
Vulnerability Retbleed: Not affected
Vulnerability Spec rstack overflow: Not affected
Vulnerability Spec store bypass: Mitigation; Speculative Store Bypass disabled via prctl and seccomp
Vulnerability Spectre v1: Mitigation; usercopy/swapgs barriers and __user pointer sanitization
Vulnerability Spectre v2: Mitigation; Enhanced / Automatic IBRS; IBPB conditional; RSB filling; PBRSB-eIBRS SW sequence; BHI SW loop, KVM SW loop
Vulnerability Srbds: Not affected
Vulnerability Tsx async abort: Not affected
Versions of relevant libraries:
[pip3] mypy-extensions==1.0.0
[pip3] numpy==2.3.3
[pip3] nvidia-cublas-cu12==12.6.4.1
[pip3] nvidia-cuda-cupti-cu12==12.6.80
[pip3] nvidia-cuda-nvrtc-cu12==12.6.77
[pip3] nvidia-cuda-runtime-cu12==12.6.77
[pip3] nvidia-cudnn-cu12==9.5.1.17
[pip3] nvidia-cufft-cu12==11.3.0.4
[pip3] nvidia-curand-cu12==10.3.7.77
[pip3] nvidia-cusolver-cu12==11.7.1.2
[pip3] nvidia-cusparse-cu12==12.5.4.2
[pip3] nvidia-cusparselt-cu12==0.6.3
[pip3] nvidia-nccl-cu12==2.21.5
[pip3] nvidia-nvjitlink-cu12==12.6.85
[pip3] nvidia-nvtx-cu12==12.6.77
[pip3] onnxruntime==1.20.1
[pip3] rapidocr-onnxruntime==1.3.24
[pip3] torch==2.6.0+cu126
[pip3] torchaudio==2.6.0+cu126
[pip3] torchvision==0.21.0+cu126
[pip3] torchviz==0.0.3
[pip3] triton==3.2.0
[conda] numpy 2.3.3 pypi_0 pypi
[conda] nvidia-cublas-cu12 12.6.4.1 pypi_0 pypi
[conda] nvidia-cuda-cupti-cu12 12.6.80 pypi_0 pypi
[conda] nvidia-cuda-nvrtc-cu12 12.6.77 pypi_0 pypi
[conda] nvidia-cuda-runtime-cu12 12.6.77 pypi_0 pypi
[conda] nvidia-cudnn-cu12 9.5.1.17 pypi_0 pypi
[conda] nvidia-cufft-cu12 11.3.0.4 pypi_0 pypi
[conda] nvidia-curand-cu12 10.3.7.77 pypi_0 pypi
[conda] nvidia-cusolver-cu12 11.7.1.2 pypi_0 pypi
[conda] nvidia-cusparse-cu12 12.5.4.2 pypi_0 pypi
[conda] nvidia-cusparselt-cu12 0.6.3 pypi_0 pypi
[conda] nvidia-nccl-cu12 2.21.5 pypi_0 pypi
[conda] nvidia-nvjitlink-cu12 12.6.85 pypi_0 pypi
[conda] nvidia-nvtx-cu12 12.6.77 pypi_0 pypi
[conda] torch 2.6.0+cu126 pypi_0 pypi
[conda] torchaudio 2.6.0+cu126 pypi_0 pypi
[conda] torchvision 0.21.0+cu126 pypi_0 pypi
[conda] torchviz 0.0.3 pypi_0 pypi
[conda] triton 3.2.0 pypi_0 pypi
Metadata
Metadata
Assignees
Labels
No labels