[Bug] 针对使用peft微调后的unet编译后生图错误

[hezeli123]

Your current environment information

libibverbs not available, ibv_fork_init skipped
Collecting environment information...
PyTorch version: 2.4.0+cu124
Is debug build: False
CUDA used to build PyTorch: 12.4
ROCM used to build PyTorch: N/A

OneFlow version: path: ['/opt/py3/lib/python3.10/site-packages/oneflow'], version: 0.9.1.dev20241121+cu122, git_commit: cbb0a3e, cmake_build_type: Release, rdma: True, mlir: True, enterprise: False
Nexfort version: none
OneDiff version: 1.2.1.dev28
OneDiffX version: 1.2.1.dev28+g424c81a8

OS: Ubuntu 22.04.4 LTS (x86_64)
GCC version: (Ubuntu 11.4.0-1ubuntu1~22.04) 11.4.0
Clang version: Could not collect
CMake version: version 3.30.4
Libc version: glibc-2.35

Python version: 3.10.12 (main, Sep 11 2024, 15:47:36) [GCC 11.4.0] (64-bit runtime)
Python platform: Linux-3.10.0-957.27.2.el7.x86_64-x86_64-with-glibc2.35
Is CUDA available: True
CUDA runtime version: Could not collect
CUDA_MODULE_LOADING set to: LAZY
GPU models and configuration: GPU 0: NVIDIA A10
Nvidia driver version: 470.82.01
cuDNN version: Could not collect
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, 48 bits virtual
Byte Order: Little Endian
CPU(s): 16
On-line CPU(s) list: 0-3
Off-line CPU(s) list: 4-15
Vendor ID: GenuineIntel
Model name: Intel(R) Xeon(R) Platinum 8369B CPU @ 2.90GHz
CPU family: 6
Model: 106
Thread(s) per core: 2
Core(s) per socket: 8
Socket(s): 1
Stepping: 6
BogoMIPS: 5800.00
Flags: fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush mmx fxsr sse sse2 ss ht syscall nx pdpe1gb rdtscp lm constant_tsc rep_good nopl xtopology nonstop_tsc eagerfpu pni pclmulqdq monitor ssse3 fma cx16 pdcm pcid sse4_1 sse4_2 x2apic movbe popcnt aes xsave avx f16c rdrand hypervisor lahf_lm abm 3dnowprefetch ssbd ibrs ibpb stibp ibrs_enhanced fsgsbase tsc_adjust bmi1 avx2 smep bmi2 erms invpcid avx512f avx512dq rdseed adx smap avx512ifma clflushopt clwb avx512cd sha_ni avx512bw avx512vl xsaveopt xsavec xgetbv1 arat avx512vbmi avx512_vbmi2 gfni vaes vpclmulqdq avx512_vnni avx512_bitalg avx512_vpopcntdq spec_ctrl intel_stibp arch_capabilities
Hypervisor vendor: KVM
Virtualization type: full
L1d cache: 384 KiB (8 instances)
L1i cache: 256 KiB (8 instances)
L2 cache: 10 MiB (8 instances)
L3 cache: 48 MiB (1 instance)
NUMA node(s): 1
NUMA node0 CPU(s): 0-15
Vulnerability L1tf: Not affected
Vulnerability Mds: Not affected
Vulnerability Meltdown: Not affected
Vulnerability Spec store bypass: Mitigation; Speculative Store Bypass disabled via prctl and seccomp
Vulnerability Spectre v1: Mitigation; Load fences, __user pointer sanitization
Vulnerability Spectre v2: Mitigation; Enhanced IBRS, IBPB

Versions of relevant libraries:
[pip3] diffusers==0.31.0
[pip3] numpy==1.26.4
[pip3] onnx==1.16.1
[pip3] onnxruntime==1.20.0
[pip3] torch==2.4.0+cu124
[pip3] torchao==0.6.1
[pip3] torchaudio==2.4.0+cu124
[pip3] torchvision==0.19.0+cu124
[pip3] transformers==4.27.1
[pip3] transformers-stream-generator==0.0.5
[pip3] triton==3.0.0
[pip3] tritonclient==2.50.0
[conda] Could not collect

🐛 Describe the bug

针对使用peft的unet进行编译会生图错误
unet = get_peft_model(unet, lora_config)
unet.load_adapter(LCM_path, adapter_name="default")
unet.merge_and_unload()
from onediff.infer_compiler import oneflow_compile
unet = oneflow_compile(unet)

[hezeli123]

使用oneflow_compile编译后，生成的图片全黑，使用torch.compile(unet)没有问题，生成的图片正常。