pytorch - 💡(How to fix) Fix Different results for with and without torch.compile on flux.1-dev model [1 participants]

🐛 Describe the bug

When testing with the diffusers flux.1-dev model, I am seeing a big difference between w/ torch.compile and w/out torch.compile for some reason. This is not true with other flux models like flux.1-schnell. Is it expected that some models will have different results depending on torch.compile behavior?

Here is a repro script: mre_compile_issue.py

Error logs

The result made with and without torch.compile have an LPIPS score of 0.34, which is fairly drastic.

Versions

(oss_dev_flashv3_diffusers) [[email protected] ~]$ with-proxy curl -sL https://raw.githubusercontent.com/pytorch/pytorch/main/torch/utils/collect_env.py | python3 Collecting environment information... PyTorch version: 2.12.0a0+gitc7e314f Is debug build: False CUDA used to build PyTorch: 12.9 ROCM used to build PyTorch: N/A

OS: CentOS Stream 9 (x86_64) GCC version: (GCC) 11.5.0 20240719 (Red Hat 11.5.0-14) Clang version: Could not collect CMake version: version 3.31.10 Libc version: glibc-2.34

Python version: 3.12.0 | packaged by Anaconda, Inc. | (main, Oct 2 2023, 17:29:18) [GCC 11.2.0] (64-bit runtime) Python platform: Linux-6.4.3-0_fbk15_hardened_2630_gf27365f948db-x86_64-with-glibc2.34 Is CUDA available: True CUDA runtime version: 12.9.86 CUDA_MODULE_LOADING set to: GPU models and configuration: GPU 0: NVIDIA H100 Nvidia driver version: 550.90.07 cuDNN version: Could not collect Is XPU available: False HIP runtime version: N/A MIOpen runtime version: N/A Is XNNPACK available: True Caching allocator config: N/A

CPU: Architecture: x86_64 CPU op-mode(s): 32-bit, 64-bit Address sizes: 52 bits physical, 57 bits virtual Byte Order: Little Endian CPU(s): 46 On-line CPU(s) list: 0-45 Vendor ID: AuthenticAMD Model name: AMD EPYC 9654 96-Core Processor CPU family: 25 Model: 17 Thread(s) per core: 1 Core(s) per socket: 46 Socket(s): 1 Stepping: 1 BogoMIPS: 4792.80 Flags: fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush mmx fxsr sse sse2 ht syscall nx mmxext fxsr_opt pdpe1gb rdtscp lm rep_good nopl cpuid extd_apicid tsc_known_freq pni pclmulqdq ssse3 fma cx16 pcid sse4_1 sse4_2 x2apic movbe popcnt tsc_deadline_timer aes xsave avx f16c rdrand hypervisor lahf_lm cmp_legacy svm cr8_legacy abm sse4a misalignsse 3dnowprefetch osvw perfctr_core invpcid_single ssbd ibrs ibpb stibp ibrs_enhanced vmmcall 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 xsaves avx512_bf16 clzero xsaveerptr wbnoinvd arat npt lbrv nrip_save tsc_scale vmcb_clean flushbyasid pausefilter pfthreshold v_vmsave_vmload vgif vnmi avx512vbmi umip pku ospke avx512_vbmi2 gfni vaes vpclmulqdq avx512_vnni avx512_bitalg avx512_vpopcntdq rdpid fsrm flush_l1d arch_capabilities Virtualization: AMD-V Hypervisor vendor: KVM Virtualization type: full L1d cache: 2.9 MiB (46 instances) L1i cache: 2.9 MiB (46 instances) L2 cache: 23 MiB (46 instances) L3 cache: 736 MiB (46 instances) NUMA node(s): 1 NUMA node0 CPU(s): 0-45 Vulnerability Gather data sampling: Not affected Vulnerability Itlb multihit: Not affected Vulnerability L1tf: Not affected Vulnerability Mds: Not affected Vulnerability Meltdown: Not affected Vulnerability Mmio stale data: Not affected Vulnerability Retbleed: Not affected Vulnerability Spec store bypass: Vulnerable Vulnerability Spectre v1: Vulnerable: __user pointer sanitization and usercopy barriers only; no swapgs barriers Vulnerability Spectre v2: Vulnerable, IBPB: disabled, STIBP: disabled, PBRSB-eIBRS: Not affected Vulnerability Srbds: Not affected Vulnerability Tsx async abort: Not affected

Versions of relevant libraries: [pip3] flake8==7.3.0 [pip3] flake8-bugbear==24.12.12 [pip3] flake8-comprehensions==3.16.0 [pip3] flake8-executable==2.1.3 [pip3] flake8-logging-format==2024.24.12 [pip3] flake8-pyi==25.5.0 [pip3] flake8_simplify==0.22.0 [pip3] mypy_extensions==1.1.0 [pip3] numpy==2.1.0 [pip3] nvidia-cublas-cu12==12.8.4.1 [pip3] nvidia-cuda-cupti-cu12==12.8.90 [pip3] nvidia-cuda-nvrtc-cu12==12.8.93 [pip3] nvidia-cuda-runtime-cu12==12.8.90 [pip3] nvidia-cudnn-cu12==9.10.2.21 [pip3] nvidia-cufft-cu12==11.3.3.83 [pip3] nvidia-curand-cu12==10.3.9.90 [pip3] nvidia-cusolver-cu12==11.7.3.90 [pip3] nvidia-cusparse-cu12==12.5.8.93 [pip3] nvidia-cusparselt-cu12==0.7.1 [pip3] nvidia-nccl-cu12==2.27.5 [pip3] nvidia-nvjitlink-cu12==12.8.93 [pip3] nvidia-nvtx-cu12==12.8.90 [pip3] optree==0.17.0 [pip3] torch==2.11.0a0+gitbf59aea [pip3] torch_c_dlpack_ext==0.1.4 [pip3] torchao==0.16.0+gita8fa9e554 [pip3] torchvision==0.25.0 [pip3] triton==3.6.0 [conda] numpy 2.1.0 pypi_0 pypi [conda] nvidia-cublas-cu12 12.8.4.1 pypi_0 pypi [conda] nvidia-cuda-cupti-cu12 12.8.90 pypi_0 pypi [conda] nvidia-cuda-nvrtc-cu12 12.8.93 pypi_0 pypi [conda] nvidia-cuda-runtime-cu12 12.8.90 pypi_0 pypi [conda] nvidia-cudnn-cu12 9.10.2.21 pypi_0 pypi [conda] nvidia-cufft-cu12 11.3.3.83 pypi_0 pypi [conda] nvidia-curand-cu12 10.3.9.90 pypi_0 pypi [conda] nvidia-cusolver-cu12 11.7.3.90 pypi_0 pypi [conda] nvidia-cusparse-cu12 12.5.8.93 pypi_0 pypi [conda] nvidia-cusparselt-cu12 0.7.1 pypi_0 pypi [conda] nvidia-nccl-cu12 2.27.5 pypi_0 pypi [conda] nvidia-nvjitlink-cu12 12.8.93 pypi_0 pypi [conda] nvidia-nvtx-cu12 12.8.90 pypi_0 pypi [conda] optree 0.17.0 pypi_0 pypi [conda] torch 2.11.0a0+gitbf59aea pypi_0 pypi [conda] torch-c-dlpack-ext 0.1.4 pypi_0 pypi [conda] torchao 0.16.0+gita8fa9e554 pypi_0 pypi [conda] torchfix 0.4.0 pypi_0 pypi [conda] torchvision 0.25.0 pypi_0 pypi [conda] triton 3.6.0 pypi_0 pypi

cc @chauhang @penguinwu