# Error testing CUDA

**URL:** <https://discourse.julialang.org/t/error-testing-cuda/132887>\
**Category:** New to Julia\
**Created:** [October 5, 2025, 12:13pm UTC](https://discourse.julialang.org/t/error-testing-cuda/132887 "2025-10-05T12:13:40Z")\
**Posts on this page:** 1\
**Page:** 1

<div class="post-metadata">

**Author:** ![dwHe123](https://sea2.discourse-cdn.com/julialang/user_avatar/discourse.julialang.org/dwhe123/32/216300_2.png) [@dwHe123](https://discourse.julialang.org/u/dwHe123)\
**Post date:** [October 5, 2025, 12:13pm UTC](https://discourse.julialang.org/t/error-testing-cuda/132887/1 "2025-10-05T12:13:40Z")

</div>

Hello everyone

I encountered a problem while testing CUDA.jl, and the same issue persists after some attempts to install different versions of CUDA.jl.I don’t know why this happen.  
I connect to a Linux server (Ubuntu 24.04.2 LTS) through VSCode, I should list some basic information first :

> julia\> CUDA.versioninfo()  
> CUDA toolchain:
> 
> - runtime 12.9, artifact installation
> - driver 570.172.8 for 12.8
> - compiler 12.9
> 
> CUDA libraries:
> 
> - CUBLAS: 12.9.1
> - CURAND: 10.3.10
> - CUFFT: 11.4.1
> - CUSOLVER: 11.7.5
> - CUSPARSE: 12.5.10
> - CUPTI: 2025.2.1 (API 28.0.0)
> - NVML: 12.0.0+570.172.8
> 
> Julia packages:
> 
> - CUDA: 5.8.3
> - CUDA\_Driver\_jll: 13.0.1+0
> - CUDA\_Compiler\_jll: 0.2.1+0
> - CUDA\_Runtime\_jll: 0.19.1+0
> 
> Toolchain:
> 
> - Julia: 1.10.10
> - LLVM: 15.0.7
> 
> 4 devices:  
> 0: NVIDIA GeForce RTX 4090 (sm\_89, 792.562 MiB / 23.988 GiB available)  
> 1: NVIDIA GeForce RTX 4090 (sm\_89, 23.524 GiB / 23.988 GiB available)  
> 2: NVIDIA GeForce RTX 4090 (sm\_89, 23.524 GiB / 23.988 GiB available)  
> 3: NVIDIA GeForce RTX 4090 (sm\_89, 23.524 GiB / 23.988 GiB available)

> julia\> versioninfo()  
> Julia Version 1.10.10  
> Commit 95f30e51f41 (2025-06-27 09:51 UTC)  
> Platform Info:  
> OS: Linux (x86\_64-linux-gnu)  
> CPU: 64 × INTEL(R) XEON(R) GOLD 6530  
> WORD\_SIZE: 64  
> LIBM: libopenlibm  
> LLVM: libLLVM-15.0.7 (ORCJIT, icelake-client)  
> Threads: 1 default, 0 interactive, 1 GC (on 64 virtual cores)  
> ‘’’  
> ‘’’  
> qtt@qt1:~$ nvidia-smi  
> Sun Oct 5 11:51:06 2025  
> ±----------------------------------------------------------------------------------------+  
> | NVIDIA-SMI 570.172.08 Driver Version: 570.172.08 CUDA Version: 12.8 |  
> |-----------------------------------------±-----------------------±---------------------+  
> | GPU Name Persistence-M | Bus-Id Disp.A | Volatile Uncorr. ECC |  
> | Fan Temp Perf Pwr:Usage/Cap | Memory-Usage | GPU-Util Compute M. |  
> | | | MIG M. |  
> |=========================================+========================+======================|  
> | 0 NVIDIA GeForce RTX 4090 Off | 00000000:27:00.0 Off | Off |  
> | 0% 29C P8 4W / 450W | 23300MiB / 24564MiB | 0% Default |  
> | | | N/A |  
> ±----------------------------------------±-----------------------±---------------------+  
> | 1 NVIDIA GeForce RTX 4090 Off | 00000000:38:00.0 Off | Off |  
> | 0% 28C P8 13W / 450W | 3MiB / 24564MiB | 0% Default |  
> | | | N/A |  
> ±----------------------------------------±-----------------------±---------------------+  
> | 2 NVIDIA GeForce RTX 4090 Off | 00000000:A8:00.0 Off | Off |  
> | 0% 31C P8 13W / 450W | 3MiB / 24564MiB | 0% Default |  
> | | | N/A |  
> ±----------------------------------------±-----------------------±---------------------+  
> | 3 NVIDIA GeForce RTX 4090 Off | 00000000:B8:00.0 Off | Off |  
> | 0% 29C P8 19W / 450W | 3MiB / 24564MiB | 0% Default |  
> | | | N/A |  
> ±----------------------------------------±-----------------------±---------------------+
> 
> ±----------------------------------------------------------------------------------------+  
> | Processes: |  
> | GPU GI CI PID Type Process name GPU Memory |  
> | ID ID Usage |  
> |=========================================================================================|  
> | 0 N/A N/A 770765 C …e/qtt/julia-1.10.10/bin/julia 1672MiB |  
> | 0 N/A N/A 770767 C …e/qtt/julia-1.10.10/bin/julia 476MiB |  
> | 0 N/A N/A 770768 C …e/qtt/julia-1.10.10/bin/julia 564MiB |  
> | 0 N/A N/A 770770 C …e/qtt/julia-1.10.10/bin/julia 5616MiB |  
> | 0 N/A N/A 770771 C …e/qtt/julia-1.10.10/bin/julia 546MiB |  
> | 0 N/A N/A 770773 C …e/qtt/julia-1.10.10/bin/julia 480MiB |  
> | 0 N/A N/A 770774 C …e/qtt/julia-1.10.10/bin/julia 670MiB |  
> | 0 N/A N/A 771159 C …e/qtt/julia-1.10.10/bin/julia 684MiB |  
> | 0 N/A N/A 774737 C …e/qtt/julia-1.10.10/bin/julia 542MiB |  
> | 0 N/A N/A 1286059 C …e/qtt/julia-1.10.10/bin/julia 4356MiB |  
> | 0 N/A N/A 1286060 C …e/qtt/julia-1.10.10/bin/julia 5646MiB |  
> | 0 N/A N/A 1286253 C …e/qtt/julia-1.10.10/bin/julia 866MiB |  
> | 0 N/A N/A 1290232 C …e/qtt/julia-1.10.10/bin/julia 544MiB |  
> | 0 N/A N/A 1290741 C …e/qtt/julia-1.10.10/bin/julia 558MiB |  
> ±----------------------------------------------------------------------------------------+

Then are the results obtained from testing CUDA：

> (@v1.10) pkg\> test CUDA  
> Testing CUDA  
> Status `/tmp/jl_TPkd71/Project.toml`  
> [621f4979] AbstractFFTs v1.5.0  
> [79e6a3ab] Adapt v4.4.0  
> [ab4f0b2a] BFloat16s v0.5.1  
> ⌃ [052768ef] CUDA v5.8.3  
> [d360d2e6] ChainRulesCore v1.26.0  
> [864edb3b] DataStructures v0.19.1  
> [7a1cc6ca] FFTW v1.10.0  
> [0c68f7d7] GPUArrays v11.2.5  
> [61eb1bfa] GPUCompiler v1.6.2  
> [a98d9a8b] Interpolations v0.16.2  
> ⌃ [033835bb] JLD2 v0.5.15  
> [63c18a36] KernelAbstractions v0.9.38  
> [5da4648a] NVTX v1.0.1  
> [a0a7dd2c] SparseMatricesCSR v0.6.9  
> [276daf66] SpecialFunctions v2.6.1  
> [90137ffa] StaticArrays v1.9.15  
> [4ee394cb] CUDA\_Driver\_jll v13.0.1+0  
> [76a88914] CUDA\_Runtime\_jll v0.19.1+0  
> [ade2ca70] Dates  
> [8ba89e20] Distributed  
> [b77e0a4c] InteractiveUtils  
> [37e2e46d] LinearAlgebra  
> [44cfe95a] Pkg v1.10.0  
> [de0858da] Printf  
> [3fa0cd96] REPL  
> [9a3f8284] Random  
> [2f01184e] SparseArrays v1.10.0  
> [10745b16] Statistics v1.10.0  
> [8dfed614] Test  
> Status `/tmp/jl_TPkd71/Manifest.toml`  
> [621f4979] AbstractFFTs v1.5.0  
> [79e6a3ab] Adapt v4.4.0  
> [a9b6321e] Atomix v1.1.2  
> [13072b0f] AxisAlgorithms v1.1.0  
> [ab4f0b2a] BFloat16s v0.5.1  
> [fa961155] CEnum v0.5.0  
> ⌃ [052768ef] CUDA v5.8.3  
> [1af6417a] CUDA\_Runtime\_Discovery v1.0.0  
> [d360d2e6] ChainRulesCore v1.26.0  
> [3da002f7] ColorTypes v0.12.1  
> [5ae59095] Colors v0.13.1  
> [34da2185] Compat v4.18.1  
> [a8cc5b0e] Crayons v4.1.1  
> [9a962f9c] DataAPI v1.16.0  
> [a93c6f00] DataFrames v1.8.0  
> [864edb3b] DataStructures v0.19.1  
> [e2d170a0] DataValueInterfaces v1.0.0  
> [ffbed154] DocStringExtensions v0.9.5  
> [e2ba6199] ExprTools v0.1.10  
> [7a1cc6ca] FFTW v1.10.0  
> [5789e2e9] FileIO v1.17.0  
> [53c48c17] FixedPointNumbers v0.8.5  
> [0c68f7d7] GPUArrays v11.2.5  
> [46192b85] GPUArraysCore v0.2.0  
> [61eb1bfa] GPUCompiler v1.6.2  
> [096a3bc2] GPUToolbox v0.3.0  
> [076d061b] HashArrayMappedTries v0.2.0  
> [842dd82b] InlineStrings v1.4.5  
> [a98d9a8b] Interpolations v0.16.2  
> [41ab1584] InvertedIndices v1.3.1  
> [92d709cd] IrrationalConstants v0.2.4  
> [82899510] IteratorInterfaceExtensions v1.0.0  
> ⌃ [033835bb] JLD2 v0.5.15  
> [692b3bcd] JLLWrappers v1.7.1  
> [63c18a36] KernelAbstractions v0.9.38  
> [929cbde3] LLVM v9.4.2  
> [8b046642] LLVMLoopInfo v1.0.0  
> [b964fa9f] LaTeXStrings v1.4.0  
> [2ab3a3ac] LogExpFunctions v0.3.29  
> [1914dd2f] MacroTools v0.5.16  
> [e1d29d7a] Missings v1.2.0  
> [5da4648a] NVTX v1.0.1  
> [6fe1bfb0] OffsetArrays v1.17.0  
> [bac558e1] OrderedCollections v1.8.1  
> [2dfb63ee] PooledArrays v1.4.3  
> ⌅ [aea7be01] PrecompileTools v1.2.1  
> [21216c6a] Preferences v1.5.0  
> ⌅ [08abe8d2] PrettyTables v2.4.0  
> [74087812] Random123 v1.7.1  
> [e6cf234a] RandomNumbers v1.6.0  
> [c84ed2f1] Ratios v0.4.5  
> [189a3867] Reexport v1.2.2  
> [ae029012] Requires v1.3.1  
> [7e506255] ScopedValues v1.5.0  
> [6c6a2e73] Scratch v1.3.0  
> [91c51154] SentinelArrays v1.4.8  
> [a2af1166] SortingAlgorithms v1.2.2  
> [a0a7dd2c] SparseMatricesCSR v0.6.9  
> [276daf66] SpecialFunctions v2.6.1  
> [90137ffa] StaticArrays v1.9.15  
> [1e83bf80] StaticArraysCore v1.4.3  
> [892a3eda] StringManipulation v0.4.1  
> [3783bdb8] TableTraits v1.0.1  
> [bd369af6] Tables v1.12.1  
> [e689c965] Tracy v0.1.6  
> [3bb67fe8] TranscodingStreams v0.11.3  
> [013be700] UnsafeAtomics v0.3.0  
> [efce3f68] WoodburyMatrices v1.0.0  
> [d1e2174e] CUDA\_Compiler\_jll v0.2.1+0  
> [4ee394cb] CUDA\_Driver\_jll v13.0.1+0  
> [76a88914] CUDA\_Runtime\_jll v0.19.1+0  
> [f5851436] FFTW\_jll v3.3.11+0  
> [1d5cc7b8] IntelOpenMP\_jll v2025.2.0+0  
> [9c1d0b0a] JuliaNVTXCallbacks\_jll v0.2.1+0  
> [dad2f222] LLVMExtra\_jll v0.0.37+2  
> [ad6e5548] LibTracyClient\_jll v0.9.1+6  
> [856f044c] MKL\_jll v2025.2.0+0  
> [e98f9f5b] NVTX\_jll v3.2.2+0  
> [efe28fd5] OpenSpecFun\_jll v0.5.6+0  
> [1e29f10c] demumble\_jll v1.3.0+0  
> [1317d2d5] oneTBB\_jll v2022.0.0+0  
> [0dad84c5] ArgTools v1.1.1  
> [56f22d72] Artifacts  
> [2a0f44e3] Base64  
> [ade2ca70] Dates  
> [8ba89e20] Distributed  
> [f43a241f] Downloads v1.6.0  
> [7b1f6079] FileWatching  
> [9fa8497b] Future  
> [b77e0a4c] InteractiveUtils  
> [4af54fe1] LazyArtifacts  
> [b27032c2] LibCURL v0.6.4  
> [76f85450] LibGit2  
> [8f399da3] Libdl  
> [37e2e46d] LinearAlgebra  
> [56ddb016] Logging  
> [d6f4376e] Markdown  
> [a63ad114] Mmap  
> [ca575930] NetworkOptions v1.2.0  
> [44cfe95a] Pkg v1.10.0  
> [de0858da] Printf  
> [3fa0cd96] REPL  
> [9a3f8284] Random  
> [ea8e919c] SHA v0.7.0  
> [9e88b42a] Serialization  
> [1a1011a3] SharedArrays  
> [6462fe0b] Sockets  
> [2f01184e] SparseArrays v1.10.0  
> [10745b16] Statistics v1.10.0  
> [4607b0f0] SuiteSparse  
> [fa267f1f] TOML v1.0.3  
> [a4e569a6] Tar v1.10.0  
> [8dfed614] Test  
> [cf7118a7] UUIDs  
> [4ec0a83e] Unicode  
> [e66e0078] CompilerSupportLibraries\_jll v1.1.1+0  
> [deac9b47] LibCURL\_jll v8.4.0+0  
> [e37daf67] LibGit2\_jll v1.6.4+0  
> [29816b5a] LibSSH2\_jll v1.11.0+1  
> [c8ffd9c3] MbedTLS\_jll v2.28.2+1  
> [14a3606d] MozillaCACerts\_jll v2023.1.10  
> [4536629a] OpenBLAS\_jll v0.3.23+4  
> [05823500] OpenLibm\_jll v0.8.5+0  
> [bea87d4a] SuiteSparse\_jll v7.2.1+1  
> [83775a58] Zlib\_jll v1.2.13+1  
> [8e850b90] libblastrampoline\_jll v5.11.0+0  
> [8e850ede] nghttp2\_jll v1.52.0+1  
> [3f19e933] p7zip\_jll v17.4.0+2  
> Info Packages marked with ⌃ and ⌅ have new versions available. Those with ⌃ may be upgradable, but those with ⌅ are restricted by compatibility constraints from upgrading.  
> Precompiling packages finished.  
> 105 dependencies successfully precompiled in 88 seconds. 7 already precompiled.  
> 1 dependency had output during precompilation:  
> ┌ MKL\_jll  
> │ Downloading artifact: IntelOpenMP  
> └  
> Testing Running tests…  
> ┌ Info: System information:  
> │ CUDA toolchain:  
> │ - runtime 12.9, artifact installation  
> │ - driver 570.172.8 for 12.8  
> │ - compiler 12.9  
> │  
> │ CUDA libraries:  
> │ - CUBLAS: 12.9.1  
> │ - CURAND: 10.3.10  
> │ - CUFFT: 11.4.1  
> │ - CUSOLVER: 11.7.5  
> │ - CUSPARSE: 12.5.10  
> │ - CUPTI: 2025.2.1 (API 28.0.0)  
> │ - NVML: 12.0.0+570.172.8  
> │  
> │ Julia packages:  
> │ - CUDA: 5.8.3  
> │ - CUDA\_Driver\_jll: 13.0.1+0  
> │ - CUDA\_Compiler\_jll: 0.2.1+0  
> │ - CUDA\_Runtime\_jll: 0.19.1+0  
> │  
> │ Toolchain:  
> │ - Julia: 1.10.10  
> │ - LLVM: 15.0.7  
> │  
> │ 4 devices:  
> │ 0: NVIDIA GeForce RTX 4090 (sm\_89, 792.562 MiB / 23.988 GiB available)  
> │ 1: NVIDIA GeForce RTX 4090 (sm\_89, 23.524 GiB / 23.988 GiB available)  
> │ 2: NVIDIA GeForce RTX 4090 (sm\_89, 23.524 GiB / 23.988 GiB available)  
> └ 3: NVIDIA GeForce RTX 4090 (sm\_89, 23.524 GiB / 23.988 GiB available)  
> [ Info: Testing using device 0 (NVIDIA GeForce RTX 4090). To change this, specify the `--gpu` argument to the tests, or set the `CUDA_VISIBLE_DEVICES` environment variable.  
> [ Info: Running 1 tests in parallel. If this is too many, specify the `--jobs` argument to the tests, or set the `JULIA_CPU_THREADS` environment variable.  
> | | ---------------- GPU ---------------- | ---------------- CPU ---------------- |  
> Test (Worker) | Time (s) | GC (s) | GC % | Alloc (MB) | RSS (MB) | GC (s) | GC % | Alloc (MB) | RSS (MB) |  
> core/initialization (2) | 5.57 | 0.00 | 0.0 | 0.00 | 416.00 | 0.01 | 0.1 | 64.24 | 1478.82 |  
> gpuarrays/reductions/sum prod (3) | 157.15 | 0.02 | 0.0 | 3.24 | 464.00 | 3.86 | 2.5 | 10638.09 | 3235.04 |  
> gpuarrays/reductions/reduce (3) | 90.22 | 0.01 | 0.0 | 1.53 | 468.00 | 2.00 | 2.2 | 8644.59 | 3901.03 |  
> gpuarrays/reductions/mapreducedim! (3) | 64.31 | 0.00 | 0.0 | 1.54 | 470.00 | 1.06 | 1.7 | 4089.67 | 4448.71 |  
> gpuarrays/broadcasting (3) | 152.41 | 0.01 | 0.0 | 2.00 | 476.00 | 2.49 | 1.6 | 9933.03 | 5858.54 |
> 
> gpuarrays/reductions/== isequal (3) | 51.18 | 0.01 | 0.0 | 1.07 | 478.00 | 1.33 | 2.6 | 5287.18 | 6211.80 |  
> gpuarrays/base (3) | 24.77 | 0.00 | 0.0 | 8.90 | 480.00 | 0.80 | 3.2 | 2581.06 | 6547.80 |  
> gpuarrays/random (3) | 24.60 | 0.00 | 0.0 | 0.03 | 480.00 | 0.20 | 0.8 | 992.90 | 6644.76 |  
> gpuarrays/vectors (3) | 0.28 | 0.00 | 0.0 | 0.00 | 480.00 | 0.00 | 0.0 | 16.54 | 6644.76 |  
> gpuarrays/ext/jld2 (3) | 7.79 | 0.00 | 0.0 | 0.00 | 480.00 | 0.05 | 0.7 | 305.04 | 6676.76 |  
> gpuarrays/constructors (3) | 22.13 | 0.00 | 0.0 | 0.65 | 480.00 | 0.30 | 1.3 | 1147.61 | 6768.30 |  
> gpuarrays/reductions/mapreduce (3) | 27.65 | 0.01 | 0.0 | 1.83 | 484.00 | 0.45 | 1.6 | 2081.10 | 6937.31 |  
> gpuarrays/statistics (3) | 55.35 | 0.00 | 0.0 | 1.51 | 498.00 | 1.02 | 1.8 | 3624.64 | 7721.31 |  
> gpuarrays/linalg/norm (3) | 121.30 | 0.01 | 0.0 | 0.02 | 502.00 | 1.63 | 1.3 | 7316.93 | 10480.56 |  
> gpuarrays/linalg/NaN\_false (3) | 14.49 | 0.00 | 0.0 | 0.00 | 502.00 | 0.12 | 0.8 | 789.30 | 10939.57 |  
> gpuarrays/math/intrinsics (3) | 1.91 | 0.00 | 0.0 | 0.00 | 502.00 | 0.00 | 0.0 | 89.65 | 10939.57 |  
> gpuarrays/linalg/mul!/matrix-matrix (3) | 81.99 | 0.01 | 0.0 | 0.13 | 506.00 | 1.39 | 1.7 | 5560.40 | 11332.05 |  
> gpuarrays/reductions/mapreducedim!\_large (3) | 9.35 | 0.00 | 0.0 | 818.38 | 698.00 | 0.16 | 1.7 | 1975.14 | 12172.28 |  
> gpuarrays/uniformscaling (3) | 6.17 | 0.00 | 0.0 | 0.01 | 698.00 | 0.00 | 0.0 | 273.53 | 12172.28 |  
> gpuarrays/reductions/minimum maximum extrema (3) | 160.92 | 0.01 | 0.0 | 2.19 | 704.00 | 2.68 | 1.7 | 10382.93 | 13841.21 |  
> gpuarrays/reductions/any all count (3) | 7.01 | 0.00 | 0.0 | 0.00 | 704.00 | 0.09 | 1.2 | 542.95 | 13858.21 |  
> gpuarrays/indexing multidimensional (3) | 41.29 | 0.00 | 0.0 | 2.07 | 774.00 | 0.70 | 1.7 | 2589.85 | 14222.71 |  
> gpuarrays/indexing find (3) | 19.74 | 0.00 | 0.0 | 0.13 | 774.00 | 0.46 | 2.3 | 1615.46 | 14508.00 |  
> gpuarrays/linalg/mul!/vector-matrix (3) | 49.20 | 0.00 | 0.0 | 0.02 | 776.00 | 0.90 | 1.8 | 3566.35 | 14734.57 |  
> gpuarrays/math/power (3) | 11.65 | 0.00 | 0.0 | 0.01 | 776.00 | 0.30 | 2.6 | 1338.47 | 14774.07 |  
> gpuarrays/linalg (3) | 145.87 | 0.45 | 0.3 | 5406.77 | 752.00 | 3.60 | 2.5 | 33870.12 | 20590.75 |  
> gpuarrays/reductions/reducedim! (3) | 0.65 | 0.00 | 0.2 | 1.03 | 752.00 | 0.00 | 0.0 | 21.84 | 20590.75 |  
> gpuarrays/indexing scalar (3) | 8.11 | 0.00 | 0.0 | 0.01 | 754.00 | 0.14 | 1.8 | 519.94 | 20590.75 |  
> gpuarrays/alloc cache (3) | 1.26 | 0.00 | 0.0 | 0.00 | 754.00 | 0.00 | 0.0 | 111.79 | 20590.75 |  
> libraries/cusparse (3) | 103.87 | 0.03 | 0.0 | 12.95 | 756.00 | 1.42 | 1.4 | 5932.16 | 20590.75 |  
> From worker 3: ERROR: a exception was thrown during kernel execution on thread (33, 1, 1) in block (2, 1, 1).  
> From worker 3: Stacktrace not available, run Julia on debug level 2 for more details (by passing -g2 to the executable).  
> From worker 3:  
> From worker 3: ERROR: a exception was thrown during kernel execution on thread (33, 1, 1) in block (2, 1, 1).  
> From worker 3: Stacktrace not available, run Julia on debug level 2 for more details (by passing -g2 to the executable).  
> From worker 3:  
> From worker 3: ERROR: a exception was thrown during kernel execution on thread (1, 1, 1) in block (2, 1, 1).  
> From worker 3: Stacktrace not available, run Julia on debug level 2 for more details (by passing -g2 to the executable).  
> From worker 3:  
> From worker 3: ERROR: a exception was thrown during kernel execution on thread (1, 1, 1) in block (2, 1, 1).  
> From worker 3: Stacktrace not available, run Julia on debug level 2 for more details (by passing -g2 to the executable).  
> From worker 3:  
> **libraries/cusolver/dense (3) | failed at 2025-10-05T11:21:03.486**  
> From worker 4: WARNING: Method definition var"#3962#kernel"(Any) in module Main at /home/qtt/.julia/packages/CUDA/Wfi8S/test/core/execution.jl:358 overwritten at /home/qtt/.julia/packages/CUDA/Wfi8S/test/core/execution.jl:366.  
> core/execution (4) | 43.10 | 0.01 | 0.0 | 0.02 | 656.00 | 1.10 | 2.6 | 3123.82 | 1527.50 |  
> **base/array (4) | failed at 2025-10-05T11:23:12.522**  
> core/cudadrv (5) | 17.04 | 0.00 | 0.0 | 0.00 | 460.00 | 0.21 | 1.3 | 1026.63 | 1478.82 |  
> libraries/cublas/level2 (6) | 56.45 | 0.01 | 0.0 | 1.35 | 538.00 | 1.60 | 2.8 | 4080.19 | 1703.36 |  
> libraries/cublas/extensions (6) | 47.60 | 0.01 | 0.0 | 36.49 | 540.00 | 1.53 | 3.2 | 3802.86 | 2064.80 |  
> libraries/cusparse/generic (6) | 69.48 | 0.04 | 0.1 | 14.32 | 546.00 | 1.10 | 1.6 | 3926.32 | 2525.03 |  
> libraries/cublas/level3 (6) | 49.36 | 0.01 | 0.0 | 5.71 | 548.00 | 0.64 | 1.3 | 2426.10 | 2876.65 |  
> From worker 6: do\_apply at /cache/build/builder-amdci5-7/julialang/julia-release-1-dot-10/src/builtins.c:768  
> From worker 6: #118 at /cache/build/builder-amdci5-7/julialang/julia-release-1-dot-10/usr/share/julia/stdlib/v1.10/Distributed/src/process\_messages.jl:310  
> From worker 6: run\_work\_thunk at /cache/build/builder-amdci5-7/julialang/julia-release-1-dot-10/usr/share/julia/stdlib/v1.10/Distributed/src/process\_messages.jl:70  
> From worker 6: #117 at /cache/build/builder-amdci5-7/julialang/julia-release-1-dot-10/usr/share/julia/stdlib/v1.10/Distributed/src/process\_messages.jl:310  
> From worker 6: unknown function (ip: 0x7466a732a282)  
> From worker 6: \_jl\_invoke at /cache/build/builder-amdci5-7/julialang/julia-release-1-dot-10/src/gf.c:2895 [inlined]  
> From worker 6: ijl\_apply\_generic at /cache/build/builder-amdci5-7/julialang/julia-release-1-dot-10/src/gf.c:3077  
> From worker 6: jl\_apply at /cache/build/builder-amdci5-7/julialang/julia-release-1-dot-10/src/julia.h:1982 [inlined]  
> From worker 6: start\_task at /cache/build/builder-amdci5-7/julialang/julia-release-1-dot-10/src/task.c:1256  
> From worker 6: error in running finalizer: CUDA.CuError(code=CUDA.cudaError\_enum(0x000002bc))  
> From worker 6: throw\_api\_error at /home/qtt/.julia/packages/CUDA/Wfi8S/lib/cudadrv/libcuda.jl:30  
> From worker 6: check at /home/qtt/.julia/packages/CUDA/Wfi8S/lib/cudadrv/libcuda.jl:37 [inlined]  
> From worker 6: cuModuleUnload at /home/qtt/.julia/packages/GPUToolbox/XaIIx/src/ccalls.jl:33 [inlined]  
> From worker 6: #989 at /home/qtt/.julia/packages/CUDA/Wfi8S/lib/cudadrv/module.jl:92 [inlined]  
> From worker 6: #context!#1025 at /home/qtt/.julia/packages/CUDA/Wfi8S/lib/cudadrv/state.jl:168 [inlined]  
> From worker 6: context! at /home/qtt/.julia/packages/CUDA/Wfi8S/lib/cudadrv/state.jl:163 [inlined]  
> From worker 6: unsafe\_unload! at /home/qtt/.julia/packages/CUDA/Wfi8S/lib/cudadrv/module.jl:91  
> From worker 6: jfptr\_unsafe\_unloadNOT.\_15636 at /home/qtt/.julia/compiled/v1.10/CUDA/oWw5k\_aU2nd.so (unknown line)  
> From worker 6: \_jl\_invoke at /cache/build/builder-amdci5-7/julialang/julia-release-1-dot-10/src/gf.c:2895 [inlined]  
> From worker 6: ijl\_apply\_generic at /cache/build/builder-amdci5-7/julialang/julia-release-1-dot-10/src/gf.c:3077  
> From worker 6: run\_finalizer at /cache/build/builder-amdci5-7/julialang/julia-release-1-dot-10/src/gc.c:318  
> From worker 6: jl\_gc\_run\_finalizers\_in\_list at /cache/build/builder-amdci5-7/julialang/julia-release-1-dot-10/src/gc.c:408  
> From worker 6: run\_finalizers at /cache/build/builder-amdci5-7/julialang/julia-release-1-dot-10/src/gc.c:454  
> From worker 6: ijl\_atexit\_hook at /cache/build/builder-amdci5-7/julialang/julia-release-1-dot-10/src/init.c:299  
> From worker 6: ijl\_exit at /cache/build/builder-amdci5-7/julialang/julia-release-1-dot-10/src/init.c:207  
> From worker 6: exit at ./initdefs.jl:28 [inlined]  
> From worker 6: exit at ./initdefs.jl:29  
> From worker 6: jfptr\_exit\_79417.1 at /home/qtt/julia-1.10.10/lib/julia/sys.so (unknown line)  
> From worker 6: \_jl\_invoke at /cache/build/builder-amdci5-7/julialang/julia-release-1-dot-10/src/gf.c:2895 [inlined]  
> From worker 6: ijl\_apply\_generic at /cache/build/builder-amdci5-7/julialang/julia-release-1-dot-10/src/gf.c:3077  
> From worker 6: jl\_apply at /cache/build/builder-amdci5-7/julialang/julia-release-1-dot-10/src/julia.h:1982 [inlined]  
> From worker 6: jl\_f\_\_call\_latest at /cache/build/builder-amdci5-7/julialang/julia-release-1-dot-10/src/builtins.c:812  
> From worker 6: #invokelatest#2 at ./essentials.jl:892 [inlined]  
> …
> 
> libraries/cusparse/interfaces (7) | 161.17 | 0.10 | 0.1 | 47.12 | 462.00 | 3.73 | 2.3 | 10386.80 | 1982.10 |  
> core/device/intrinsics/wmma (7) | 60.04 | 0.01 | 0.0 | 0.63 | 466.00 | 0.94 | 1.6 | 4089.82 | 2973.38 |  
> libraries/cufft (7) | 76.81 | 0.01 | 0.0 | 198.03 | 566.00 | 1.80 | 2.3 | 5875.49 | 3464.22 |  
> core/device/intrinsics/atomics (7) | 18.56 | 0.00 | 0.0 | 0.00 | 566.00 | 0.20 | 1.1 | 943.82 | 3845.84 |  
> …  
> From worker 7: context! at /home/qtt/.julia/packages/CUDA/Wfi8S/lib/cudadrv/state.jl:163 [inlined]  
> From worker 7: unsafe\_unload! at /home/qtt/.julia/packages/CUDA/Wfi8S/lib/cudadrv/module.jl:91  
> From worker 7: jfptr\_unsafe\_unloadNOT.\_15636 at /home/qtt/.julia/compiled/v1.10/CUDA/oWw5k\_aU2nd.so (unknown line)  
> From worker 7: \_jl\_invoke at /cache/build/builder-amdci5-7/julialang/julia-release-1-dot-10/src/gf.c:2895 [inlined]  
> From worker 7: ijl\_apply\_generic at /cache/build/builder-amdci5-7/julialang/julia-release-1-dot-10/src/gf.c:3077  
> From worker 7: run\_finalizer at /cache/build/builder-amdci5-7/julialang/julia-release-1-dot-10/src/gc.c:318  
> From worker 7: jl\_gc\_run\_finalizers\_in\_list at /cache/build/builder-amdci5-7/julialang/julia-release-1-dot-10/src/gc.c:408  
> From worker 7: run\_finalizers at /cache/build/builder-amdci5-7/julialang/julia-release-1-dot-10/src/gc.c:454  
> From worker 7: ijl\_atexit\_hook at /cache/build/builder-amdci5-7/julialang/julia-release-1-dot-10/src/init.c:299  
> From worker 7: ijl\_exit at /cache/build/builder-amdci5-7/julialang/julia-release-1-dot-10/src/init.c:207  
> From worker 7: exit at ./initdefs.jl:28 [inlined]  
> From worker 7: exit at ./initdefs.jl:29  
> From worker 7: jfptr\_exit\_79417.1 at /home/qtt/julia-1.10.10/lib/julia/sys.so (unknown line)  
> From worker 7: \_jl\_invoke at /cache/build/builder-amdci5-7/julialang/julia-release-1-dot-10/src/gf.c:2895 [inlined]  
> From worker 7: ijl\_apply\_generic at /cache/build/builder-amdci5-7/julialang/julia-release-1-dot-10/src/gf.c:3077  
> From worker 7: jl\_apply at /cache/build/builder-amdci5-7/julialang/julia-release-1-dot-10/src/julia.h:1982 [inlined]  
> From worker 7: jl\_f\_\_call\_latest at /cache/build/builder-amdci5-7/julialang/julia-release-1-dot-10/src/builtins.c:812  
> From worker 7: #invokelatest#2 at ./essentials.jl:892 [inlined]  
> From worker 7: invokelatest at ./essentials.jl:889  
> From worker 7: unknown function (ip: 0x7a85fdd2c265)  
> From worker 7: \_jl\_invoke at /cache/build/builder-amdci5-7/julialang/julia-release-1-dot-10/src/gf.c:2895 [inlined]  
> From worker 7: ijl\_apply\_generic at /cache/build/builder-amdci5-7/julialang/julia-release-1-dot-10/src/gf.c:3077  
> From worker 7: jl\_apply at /cache/build/builder-amdci5-7/julialang/julia-release-1-dot-10/src/julia.h:1982 [inlined]  
> From worker 7: do\_apply at /cache/build/builder-amdci5-7/julialang/julia-release-1-dot-10/src/builtins.c:768  
> From worker 7: #118 at /cache/build/builder-amdci5-7/julialang/julia-release-1-dot-10/usr/share/julia/stdlib/v1.10/Distributed/src/process\_messages.jl:310  
> From worker 7: run\_work\_thunk at /cache/build/builder-amdci5-7/julialang/julia-release-1-dot-10/usr/share/julia/stdlib/v1.10/Distributed/src/process\_messages.jl:70  
> From worker 7: #117 at /cache/build/builder-amdci5-7/julialang/julia-release-1-dot-10/usr/share/julia/stdlib/v1.10/Distributed/src/process\_messages.jl:310  
> From worker 7: unknown function (ip: 0x7a85fdd28282)  
> From worker 7: \_jl\_invoke at /cache/build/builder-amdci5-7/julialang/julia-release-1-dot-10/src/gf.c:2895 [inlined]  
> From worker 7: ijl\_apply\_generic at /cache/build/builder-amdci5-7/julialang/julia-release-1-dot-10/src/gf.c:3077  
> From worker 7: jl\_apply at /cache/build/builder-amdci5-7/julialang/julia-release-1-dot-10/src/julia.h:1982 [inlined]  
> From worker 7: start\_task at /cache/build/builder-amdci5-7/julialang/julia-release-1-dot-10/src/task.c:1256  
> From worker 7: error in running finalizer: CUDA.CuError(code=CUDA.cudaError\_enum(0x000002bc))  
> From worker 7: throw\_api\_error at /home/qtt/.julia/packages/CUDA/Wfi8S/lib/cudadrv/libcuda.jl:30  
> From worker 7: check at /home/qtt/.julia/packages/CUDA/Wfi8S/lib/cudadrv/libcuda.jl:37 [inlined]  
> From worker 7: cuModuleUnload at /home/qtt/.julia/packages/GPUToolbox/XaIIx/src/ccalls.jl:33 [inlined]  
> From worker 7: #989 at /home/qtt/.julia/packages/CUDA/Wfi8S/lib/cudadrv/module.jl:92 [inlined]  
> From worker 7: #context!#1025 at /home/qtt/.julia/packages/CUDA/Wfi8S/lib/cudadrv/state.jl:168 [inlined]  
> ┌ Warning: Failed to gracefully kill worker 7, sending SIGTERM  
> └ @ Distributed ~/julia-1.10.10/share/julia/stdlib/v1.10/Distributed/src/managers.jl:745  
> From worker 7: exit at ./initdefs.jl:28 [inlined]  
> From worker 7: exit at ./initdefs.jl:29  
> From worker 7:  
> From worker 7: [1683147] signal (15): Terminated  
> From worker 7: in expression starting at none:0  
> ERROR: ┌ Warning: Worker 7 ignored SIGTERM, sending SIGKILL  
> └ @ Distributed ~/julia-1.10.10/share/julia/stdlib/v1.10/Distributed/src/managers.jl:750  
> LoadError: TaskFailedException  
> nested task error: rmprocs: pids [7] not terminated after 30 seconds.  
> Stacktrace:  
> [1] \_rmprocs(pids::Vector{Int64}, waitfor::Int64)  
> @ Distributed ~/julia-1.10.10/share/julia/stdlib/v1.10/Distributed/src/cluster.jl:1069  
> [2] rmprocs(pids::Int64; waitfor::Int64)  
> @ Distributed ~/julia-1.10.10/share/julia/stdlib/v1.10/Distributed/src/cluster.jl:1037  
> [3] rmprocs  
> @ ~/julia-1.10.10/share/julia/stdlib/v1.10/Distributed/src/cluster.jl:1028 [inlined]  
> [4] (::var"#recycle\_worker#57")(p::Int64)  
> @ Main ~/.julia/packages/CUDA/Wfi8S/test/runtests.jl:353  
> [5] (::var"#52#59"{Dict{String, DateTime}, Task, var"#recycle\_worker#57"})()  
> @ Main ~/.julia/packages/CUDA/Wfi8S/test/runtests.jl:395  
> Stacktrace:  
> [1] sync\_end(c::Channel{Any})  
> @ Base ./task.jl:455  
> [2] macro expansion  
> @ task.jl:487 [inlined]  
> [3] top-level scope  
> @ ~/.julia/packages/CUDA/Wfi8S/test/runtests.jl:344  
> [4] include(fname::String)  
> @ Base.MainInclude ./client.jl:494  
> [5] top-level scope  
> @ none:6  
> in expression starting at /home/qtt/.julia/packages/CUDA/Wfi8S/test/runtests.jl:314  
> ERROR: Package CUDA errored during testing

I omitted a lot of information about “from worker 6” and “from worker 7” above because it was too long to list here.  
This problem has been bothering me for many days. I would be very grateful if you could help me.  
If there is anything wrong with the way I am asking questions, I sincerely ask everyone to point it out. This is my first time asking a question in this community. Thank you.