pytorch
pytorch copied to clipboard
Published
20 hours ago •
pytorch
pytorch
Torch 2.6 Amd CPU NVIDIA GPU
🐛 Describe the bug
When trying to compile the lattest torch version on my amd system. the compilation failed. In order for it to compile i had to modify a file which i specified below.
So i had to modify this file to get it to compile also once installed torch vision would no longer work and audio. so i compiled them and it seems to now work. The file i had to modify to get it to compile was . /home/myles/pytorch/test/cpp/api/CMakeLists.txt at line 59 replaced that text below.
I ran a test with a vision model to confirm its all working: Generated response: <|begin_of_text|><|start_header_id|>user<|end_header_id|>
<|image|>Please provide a thorough and vivid description of this image to create high-quality training data for a new LLM. If the image features text, transcribe it exactly as it appears, capturing every word and detail. In cases where the image quality is poor or unclear, provide a detailed analysis of its shortcomings, including any distortions, blurriness, or other factors affecting clarity. Ensure that every significant aspect of the image is documented—consider elements such as colors, shapes, textures, and any context that may enhance understanding. If the image contains nudity or other potentially unethical content, describe it in a straightforward manner without moral judgement, as this information is essential for training data. The new LLM must learn to interpret and distinguish all types of images, so your detailed and accurate outputs are crucial. Additionally, feel free to share your personal thoughts or insights about the image at the end of your description if you feel inspired to do so. Avoid mentioning that you are creating training data in your output, and strive to use varied language to keep your description engaging.<|eot_id|><|start_header_id|>assistant<|end_header_id|>
This image presents a photograph of a Scrabble game board featuring the letters S, U, C, C, E, S prominently displayed in the center. The letters are arranged in columns and rows across the board, with other letters and words printed in black on tan squares.
The Scrabble board is predominantly tan, outlined in red, and has white lines separating the squares. The letters "S", "C", "R", "A", "B", "L", "E" are printed in black on the sides of the board. The game board is set against a white background.
. /home/myles/pytorch/test/cpp/api/CMakeLists.txt at line 59 replaced that text below.
if(NOT MSVC)
# Clang has an unfixed bug leading to spurious missing braces warnings
# see https://bugs.llvm.org/show_bug.cgi?id=21629
target_compile_options_if_supported(test_api "-Wno-missing-braces")
# Considered to be flaky. See the discussion at
# https://github.com/pytorch/pytorch/pull/9608
target_compile_options_if_supported(test_api "-Wno-maybe-uninitialized")
# gcc gives nonsensical warnings about variadic.h
target_compile_options_if_supported(test_api "-Wno-unused-but-set-parameter")
# Suppress warnings for deprecated declarations and nonnull errors
target_compile_options(test_api PRIVATE "-Wno-deprecated-declarations" "-Wno-error=nonnull")
endif()
Error logs
FAILED: test_api/CMakeFiles/test_api.dir/dataloader.cpp.o
/usr/bin/ccache /usr/bin/c++ -DFLASHATTENTION_DISABLE_ALIBI -DHAVE_MALLOC_USABLE_SIZE=1 -DHAVE_MMAP=1 -DHAVE_SHM_OPEN=1 -DHAVE_SHM_UNLINK=1 -DIDEEP_USE_MKL -DMINIZ_DISABLE_ZIP_READER_CRC32_CHECKS -DONNXIFI_ENABLE_EXT=1 -DONNX_ML=1 -DONNX_NAMESPACE=onnx_torch -DUSE_C10D_GLOO -DUSE_C10D_MPI -DUSE_C10D_NCCL -DUSE_CUDA -DUSE_DISTRIBUTED -DUSE_EXTERNAL_MZCRC -DUSE_RPC -DUSE_TENSORPIPE -D_FILE_OFFSET_BITS=64 -I/home/myles/pytorch/build/aten/src -I/home/myles/pytorch/aten/src -I/home/myles/pytorch/build -I/home/myles/pytorch -I/home/myles/pytorch/cmake/../third_party/benchmark/include -I/home/myles/pytorch/third_party/onnx -I/home/myles/pytorch/build/third_party/onnx -I/home/myles/pytorch/nlohmann -I/home/myles/pytorch/build/caffe2/../aten/src -I/home/myles/pytorch/torch/csrc/api -I/home/myles/pytorch/torch/csrc/api/include -I/home/myles/pytorch/c10/.. -I/home/myles/pytorch/c10/cuda/../.. -isystem /home/myles/pytorch/build/third_party/gloo -isystem /home/myles/pytorch/cmake/../third_party/gloo -isystem /home/myles/pytorch/cmake/../third_party/tensorpipe/third_party/libuv/include -isystem /home/myles/pytorch/cmake/../third_party/googletest/googlemock/include -isystem /home/myles/pytorch/cmake/../third_party/googletest/googletest/include -isystem /home/myles/pytorch/third_party/protobuf/src -isystem /home/myles/pytorch/third_party/XNNPACK/include -isystem /home/myles/pytorch/third_party/ittapi/include -isystem /home/myles/pytorch/cmake/../third_party/eigen -isystem /usr/local/cuda-12.4/include -isystem /home/myles/pytorch/third_party/ideep/mkl-dnn/include/oneapi/dnnl -isystem /home/myles/pytorch/third_party/ideep/include -isystem /home/myles/pytorch/INTERFACE -isystem /home/myles/pytorch/third_party/nlohmann/include -isystem /home/myles/pytorch/third_party/googletest/googletest/include -isystem /home/myles/pytorch/third_party/googletest/googletest -D_GLIBCXX_USE_CXX11_ABI=1 -Wno-error -Wno-non-virtual-dtor -Wno-return-type -fvisibility-inlines-hidden -DUSE_PTHREADPOOL -DNDEBUG -DUSE_KINETO -DLIBKINETO_NOROCTRACER -DLIBKINETO_NOXPUPTI=ON -DUSE_FBGEMM -DUSE_PYTORCH_QNNPACK -DUSE_XNNPACK -DSYMBOLICATE_MOBILE_DEBUG_HANDLE -O2 -fPIC -Wall -Wextra -Werror=return-type -Werror=non-virtual-dtor -Werror=range-loop-construct -Werror=bool-operation -Wnarrowing -Wno-missing-field-initializers -Wno-type-limits -Wno-array-bounds -Wno-unknown-pragmas -Wno-unused-parameter -Wno-strict-overflow -Wno-strict-aliasing -Wno-stringop-overflow -Wsuggest-override -Wno-psabi -Wno-error=old-style-cast -Wno-missing-braces -fdiagnostics-color=always -faligned-new -Wno-unused-but-set-variable -Wno-maybe-uninitialized -fno-math-errno -fno-trapping-math -Werror=format -Wno-stringop-overflow -DHAVE_AVX512_CPU_DEFINITION -DHAVE_AVX2_CPU_DEFINITION -O3 -DNDEBUG -DNDEBUG -std=gnu++17 -fPIE -DMKL_HAS_SBGEMM -DMKL_HAS_SHGEMM -DTORCH_USE_LIBUV -DCAFFE2_USE_GLOO -Wno-missing-braces -Wno-maybe-uninitialized -Wno-unused-but-set-parameter -MD -MT test_api/CMakeFiles/test_api.dir/dataloader.cpp.o -MF test_api/CMakeFiles/test_api.dir/dataloader.cpp.o.d -o test_api/CMakeFiles/test_api.dir/dataloader.cpp.o -c /home/myles/pytorch/test/cpp/api/dataloader.cpp
In file included from /usr/include/c++/12/bits/stl_uninitialized.h:63,
from /usr/include/c++/12/memory:65,
from /home/myles/pytorch/third_party/googletest/googletest/include/gtest/gtest.h:57,
from /home/myles/pytorch/test/cpp/api/dataloader.cpp:1:
In static member function ‘static _Tp* std::__copy_move<_IsMove, true, std::random_access_iterator_tag>::__copy_m(const _Tp*, const _Tp*, _Tp*) [with _Tp = long unsigned int; bool _IsMove = false]’,
inlined from ‘_OI std::__copy_move_a2(_II, _II, _OI) [with bool _IsMove = false; _II = const long unsigned int*; _OI = long unsigned int*]’ at /usr/include/c++/12/bits/stl_algobase.h:495:30,
inlined from ‘_OI std::__copy_move_a1(_II, _II, _OI) [with bool _IsMove = false; _II = const long unsigned int*; _OI = long unsigned int*]’ at /usr/include/c++/12/bits/stl_algobase.h:522:42,
inlined from ‘_OI std::__copy_move_a(_II, _II, _OI) [with bool _IsMove = false; _II = __gnu_cxx::__normal_iterator<const long unsigned int*, vector<long unsigned int> >; _OI = __gnu_cxx::__normal_iterator<long unsigned int*, vector<long unsigned int> >]’ at /usr/include/c++/12/bits/stl_algobase.h:529:31,
inlined from ‘_OI std::copy(_II, _II, _OI) [with _II = __gnu_cxx::__normal_iterator<const long unsigned int*, vector<long unsigned int> >; _OI = __gnu_cxx::__normal_iterator<long unsigned int*, vector<long unsigned int> >]’ at /usr/include/c++/12/bits/stl_algobase.h:620:7,
inlined from ‘std::vector<_Tp, _Alloc>& std::vector<_Tp, _Alloc>::operator=(const std::vector<_Tp, _Alloc>&) [with _Tp = long unsigned int; _Alloc = std::allocator<long unsigned int>]’ at /usr/include/c++/12/bits/vector.tcc:244:21:
/usr/include/c++/12/bits/stl_algobase.h:431:30: error: argument 1 null where non-null expected [-Werror=nonnull]
431 | __builtin_memmove(__result, __first, sizeof(_Tp) * _Num);
| ~~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
/usr/include/c++/12/bits/stl_algobase.h:431:30: note: in a call to built-in function ‘void* __builtin_memmove(void*, const void*, long unsigned int)’
cc1plus: some warnings being treated as errors
Minified repro
No response
Versions
curl -OL https://raw.githubusercontent.com/pytorch/pytorch/main/torch/utils/collect_env.py
# For security purposes, please check the contents of collect_env.py before running it.
python3 collect_env.py
% Total % Received % Xferd Average Speed Time Time Time Current
Dload Upload Total Spent Left Speed
100 23357 100 23357 0 0 63001 0 --:--:-- --:--:-- --:--:-- 63127
Collecting environment information...
PyTorch version: 2.6.0a0+gite248c1d
Is debug build: False
CUDA used to build PyTorch: 12.4
ROCM used to build PyTorch: N/A
OS: Ubuntu 22.04.4 LTS (x86_64)
GCC version: (Ubuntu 12.3.0-1ubuntu1~22.04) 12.3.0
Clang version: 14.0.0-1ubuntu1.1
CMake version: version 3.30.2
Libc version: glibc-2.35
Python version: 3.12.6 (main, Sep 7 2024, 19:24:43) [GCC 12.3.0] (64-bit runtime)
Python platform: Linux-6.8.0-44-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
GPU 2: NVIDIA GeForce RTX 4090
GPU 3: NVIDIA GeForce RTX 4090
GPU 4: NVIDIA GeForce RTX 4090
GPU 5: NVIDIA GeForce RTX 4090
GPU 6: NVIDIA GeForce RTX 4090
GPU 7: NVIDIA GeForce RTX 4090
Nvidia driver version: 550.90.07
cuDNN version: Probably one of the following:
/usr/lib/x86_64-linux-gnu/libcudnn.so.9.5.0
/usr/lib/x86_64-linux-gnu/libcudnn_adv.so.9.5.0
/usr/lib/x86_64-linux-gnu/libcudnn_cnn.so.9.5.0
/usr/lib/x86_64-linux-gnu/libcudnn_engines_precompiled.so.9.5.0
/usr/lib/x86_64-linux-gnu/libcudnn_engines_runtime_compiled.so.9.5.0
/usr/lib/x86_64-linux-gnu/libcudnn_graph.so.9.5.0
/usr/lib/x86_64-linux-gnu/libcudnn_heuristic.so.9.5.0
/usr/lib/x86_64-linux-gnu/libcudnn_ops.so.9.5.0
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: 43 bits physical, 48 bits virtual
Byte Order: Little Endian
CPU(s): 128
On-line CPU(s) list: 0-127
Vendor ID: AuthenticAMD
Model name: AMD Ryzen Threadripper PRO 3995WX 64-Cores
CPU family: 23
Model: 49
Thread(s) per core: 2
Core(s) per socket: 64
Socket(s): 1
Stepping: 0
Frequency boost: enabled
CPU max MHz: 4308.3979
CPU min MHz: 2200.0000
BogoMIPS: 5389.69
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 constant_tsc rep_good nopl nonstop_tsc cpuid extd_apicid aperfmperf rapl pni pclmulqdq monitor ssse3 fma cx16 sse4_1 sse4_2 x2apic movbe popcnt aes xsave avx f16c rdrand lahf_lm cmp_legacy svm extapic cr8_legacy abm sse4a misalignsse 3dnowprefetch osvw ibs skinit wdt tce topoext perfctr_core perfctr_nb bpext perfctr_llc mwaitx cpb cat_l3 cdp_l3 hw_pstate ssbd mba ibpb stibp vmmcall fsgsbase bmi1 avx2 smep bmi2 cqm rdt_a rdseed adx smap clflushopt clwb sha_ni xsaveopt xsavec xgetbv1 cqm_llc cqm_occup_llc cqm_mbm_total cqm_mbm_local clzero irperf xsaveerptr rdpru wbnoinvd amd_ppin arat npt lbrv svm_lock nrip_save tsc_scale vmcb_clean flushbyasid decodeassists pausefilter pfthreshold avic v_vmsave_vmload vgif v_spec_ctrl umip rdpid overflow_recov succor smca sev sev_es
Virtualization: AMD-V
L1d cache: 2 MiB (64 instances)
L1i cache: 2 MiB (64 instances)
L2 cache: 32 MiB (64 instances)
L3 cache: 256 MiB (16 instances)
NUMA node(s): 1
NUMA node0 CPU(s): 0-127
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 Reg file data sampling: Not affected
Vulnerability Retbleed: Mitigation; untrained return thunk; SMT enabled with STIBP protection
Vulnerability Spec rstack overflow: Mitigation; Safe RET
Vulnerability Spec store bypass: Mitigation; Speculative Store Bypass disabled via prctl
Vulnerability Spectre v1: Mitigation; usercopy/swapgs barriers and __user pointer sanitization
Vulnerability Spectre v2: Mitigation; Retpolines; IBPB conditional; STIBP always-on; RSB filling; PBRSB-eIBRS Not affected; BHI Not affected
Vulnerability Srbds: Not affected
Vulnerability Tsx async abort: Not affected
Versions of relevant libraries:
[pip3] mypy-extensions==1.0.0
[pip3] numpy==2.1.2
[pip3] onnx==1.17.0
[pip3] onnxruntime==1.19.2
[pip3] open_clip_torch==2.26.1
[pip3] optree==0.12.1
[pip3] pytorch-triton==3.0.0+757b6a61e7
[pip3] torch==2.6.0a0+gite248c1d
[pip3] torchaudio==2.5.0a0+b4a286a
[pip3] torchvision==0.20.0a0+945bdad
[pip3] triton==3.0.0
[conda] Could not collect
cc @ezyang @chauhang @penguinwu
