hao-ai-lab
[Bug] Large test error for gQ Avg / Rel gQ Max
Describe the bug
First of all, thank you very much for your great work! When I run the test script test_vsa.py, I obtain the following results:
It seems that the error on gQ is significantly higher than the others (e.g., ~2e-2 for Avg vs. 2e-4, and ~1.7e1 vs. ~1e-1 for Rel Max). Is this behavior correct or expected? I look forward to your reply.
Reproduction
python tests/test_vsa.py
Environment
Collecting environment information... PyTorch version: 2.7.0a0+7c8ec84dab.nv25.03 Is debug build: False CUDA used to build PyTorch: 12.8 ROCM used to build PyTorch: N/A
OS: Ubuntu 24.04.1 LTS (x86_64) GCC version: (Ubuntu 13.3.0-6ubuntu2~24.04) 13.3.0 Clang version: Could not collect CMake version: version 3.31.6 Libc version: glibc-2.39
Python version: 3.12.3 (main, Feb 4 2025, 14:48:35) [GCC 13.3.0] (64-bit runtime) Python platform: Linux-5.15.0-91-generic-x86_64-with-glibc2.39 Is CUDA available: True CUDA runtime version: 12.8.93 CUDA_MODULE_LOADING set to: LAZY GPU models and configuration: GPU 0: NVIDIA A100-SXM4-80GB GPU 1: NVIDIA A100-SXM4-80GB GPU 2: NVIDIA A100-SXM4-80GB GPU 3: NVIDIA A100-SXM4-80GB GPU 4: NVIDIA A100-SXM4-80GB GPU 5: NVIDIA A100-SXM4-80GB GPU 6: NVIDIA A100-SXM4-80GB GPU 7: NVIDIA A100-SXM4-80GB
Nvidia driver version: 550.163.01 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 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): 128 On-line CPU(s) list: 0-127 Vendor ID: GenuineIntel Model name: Intel(R) Xeon(R) Platinum 8336C CPU @ 2.30GHz CPU family: 6 Model: 106 Thread(s) per core: 2 Core(s) per socket: 32 Socket(s): 2 Stepping: 6 CPU(s) scaling MHz: 86% CPU max MHz: 3500.0000 CPU min MHz: 800.0000 BogoMIPS: 4600.00 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: 3 MiB (64 instances) L1i cache: 2 MiB (64 instances) L2 cache: 80 MiB (64 instances) L3 cache: 108 MiB (2 instances) NUMA node(s): 2 NUMA node0 CPU(s): 0-31,64-95 NUMA node1 CPU(s): 32-63,96-127 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 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 IBRS, IBPB conditional, RSB filling, PBRSB-eIBRS SW sequence Vulnerability Srbds: Not affected Vulnerability Tsx async abort: Not affected
Versions of relevant libraries: [pip3] accelerate==1.6.0 [pip3] accelerated-scan==0.2.0 [pip3] mypy-extensions==1.0.0 [pip3] numpy==1.26.4 [pip3] nvidia-cuda-nvrtc-cu12==12.8.93 [pip3] nvidia-cudnn-frontend==1.10.0 [pip3] nvidia-dali-cuda120==1.47.0 [pip3] nvidia_lm_eval==25.3 [pip3] nvidia-ml-py==12.570.86 [pip3] nvidia-modelopt==0.25.0 [pip3] nvidia-modelopt-core==0.25.0 [pip3] nvidia-nccl-cu12==2.26.2 [pip3] nvidia-nvimgcodec-cu12==0.4.1.21 [pip3] nvidia-nvjpeg2k-cu12==0.8.1.40 [pip3] nvidia-nvtiff-cu12==0.4.0.62 [pip3] nvidia-pytriton==0.5.14 [pip3] nvidia-resiliency-ext==0.3.0 [pip3] onnx==1.17.0 [pip3] onnx-graphsurgeon==0.5.7 [pip3] open-clip-torch==2.24.0 [pip3] optree==0.14.1 [pip3] peft==0.15.1 [pip3] pynvml==12.0.0 [pip3] pytorch-lightning==2.5.1 [pip3] pytorch-triton==3.2.0+gitb2684bf3b.nvinternal [pip3] pyzmq==26.2.1 [pip3] sentence-transformers==4.0.2 [pip3] taming-transformers==0.0.1 [pip3] torch==2.7.0a0+7c8ec84dab.nv25.3 [pip3] torch-geometric==2.6.1 [pip3] torch_tensorrt==2.7.0a0 [pip3] torchdiffeq==0.2.5 [pip3] torchmetrics==1.7.0 [pip3] torchprofile==0.0.4 [pip3] torchsde==0.2.6 [pip3] torchvision==0.22.0a0 [pip3] torchx==0.7.0 [pip3] transformers==4.48.3 [pip3] triton==3.4.0 [pip3] tritonclient==2.51.0 [conda] Could not collect FastVideo Version: FastVideo Build Flags: CUDA Archs: 7.5 8.0 8.6 9.0 10.0 12.0+PTX; ROCm: Disabled; Neuron: Disabled GPU Topology: GPU0 GPU1 GPU2 GPU3 GPU4 GPU5 GPU6 GPU7 NIC0 NIC1 NIC2 NIC3 CPU Affinity NUMA Affinity GPU NUMA ID GPU0 X NV12 NV12 NV12 NV12 NV12 NV12 NV12 PXB NODE SYS SYS 0-31,64-95 0 N/A GPU1 NV12 X NV12 NV12 NV12 NV12 NV12 NV12 PXB NODE SYS SYS 0-31,64-95 0 N/A GPU2 NV12 NV12 X NV12 NV12 NV12 NV12 NV12 NODE PXB SYS SYS 0-31,64-95 0 N/A GPU3 NV12 NV12 NV12 X NV12 NV12 NV12 NV12 NODE PXB SYS SYS 0-31,64-95 0 N/A GPU4 NV12 NV12 NV12 NV12 X NV12 NV12 NV12 SYS SYS PXB NODE 32-63,96-127 1 N/A GPU5 NV12 NV12 NV12 NV12 NV12 X NV12 NV12 SYS SYS PXB NODE 32-63,96-127 1 N/A GPU6 NV12 NV12 NV12 NV12 NV12 NV12 X NV12 SYS SYS NODE PXB 32-63,96-127 1 N/A GPU7 NV12 NV12 NV12 NV12 NV12 NV12 NV12 X SYS SYS NODE PXB 32-63,96-127 1 N/A NIC0 PXB PXB NODE NODE SYS SYS SYS SYS X NODE SYS SYS NIC1 NODE NODE PXB PXB SYS SYS SYS SYS NODE X SYS SYS NIC2 SYS SYS SYS SYS PXB PXB NODE NODE SYS SYS X NODE NIC3 SYS SYS SYS SYS NODE NODE PXB PXB SYS SYS NODE X
Legend:
X = Self SYS = Connection traversing PCIe as well as the SMP interconnect between NUMA nodes (e.g., QPI/UPI) NODE = Connection traversing PCIe as well as the interconnect between PCIe Host Bridges within a NUMA node PHB = Connection traversing PCIe as well as a PCIe Host Bridge (typically the CPU) PXB = Connection traversing multiple PCIe bridges (without traversing the PCIe Host Bridge) PIX = Connection traversing at most a single PCIe bridge NV# = Connection traversing a bonded set of # NVLinks
NIC Legend:
NIC0: mlx5_1 NIC1: mlx5_2 NIC2: mlx5_3 NIC3: mlx5_4
NVIDIA_VISIBLE_DEVICES=all CUBLAS_VERSION=12.8.4.1 NVIDIA_REQUIRE_CUDA=cuda>=9.0 CUDA_CACHE_DISABLE=1 TORCH_CUDA_ARCH_LIST=7.5 8.0 8.6 9.0 10.0 12.0+PTX NCCL_VERSION=2.25.1 NVIDIA_DRIVER_CAPABILITIES=compute,utility,video TORCH_NCCL_USE_COMM_NONBLOCKING=0 NVIDIA_PRODUCT_NAME=NeMo Framework CUDA_VERSION=12.8.1.012 PYTORCH_VERSION=2.7.0a0+7c8ec84 PYTORCH_BUILD_NUMBER=0 CUBLASMP_VERSION=0.4.0.789 NVIDIA_BIGNLP_VERSION= CUDNN_FRONTEND_VERSION=1.10.0 CUDNN_VERSION=9.8.0.87 PYTORCH_HOME=/opt/pytorch/pytorch LD_LIBRARY_PATH=/usr/local/lib/python3.12/dist-packages/torch/lib:/usr/local/lib/python3.12/dist-packages/torch_tensorrt/lib:/usr/local/cuda/compat/lib:/usr/local/nvidia/lib:/usr/local/nvidia/lib64:/usr/local/cuda/lib64:/usr/local/tensorrt/lib:/usr/local/cuda/lib64:/usr/local/tensorrt/lib:/usr/local/cuda/lib64:/usr/local/tensorrt/lib NVIDIA_BUILD_ID=148941828 CUDA_DRIVER_VERSION=570.124.06 PYTORCH_BUILD_VERSION=2.7.0a0+7c8ec84 CUDA_HOME=/usr/local/cuda CUDA_MODULE_LOADING=LAZY NVIDIA_REQUIRE_JETPACK_HOST_MOUNTS= NVIDIA_PYTORCH_VERSION=25.03 TORCH_ALLOW_TF32_CUBLAS_OVERRIDE=1
