# CUDA error #218 **URL:** \ **Category:** User discussions\ **Tags:** mdrun\ **Created:** [September 26, 2025, 1:03am UTC](https://gromacs.bioexcel.eu/t/cuda-error-218/12691 "2025-09-26T01:03:48Z")\ **Posts on this page:** 4\ **Page:** 1
**Author:** ![Lgsus555](https://avatars.discourse-cdn.com/v4/letter/l/ad7895/32.png) [@Lgsus555](https://gromacs.bioexcel.eu/u/Lgsus555)\ **Post date:** [September 26, 2025, 1:03am UTC](https://gromacs.bioexcel.eu/t/cuda-error-218/12691/1 "2025-09-26T01:03:48Z")
GROMACS version:2025.3-conda\_forge GROMACS modification: Yes/No Here post your question **Subject:** CUDA Error #218 (cudaErrorInvalidPtx) with RTX 5060 when running gmx mdrun **Message:** Hello, I’m trying to run a molecular dynamics simulation using `gmx mdrun` but keep getting a CUDA error #218 with my new RTX 5060 GPU. The error occurs during the kernel launch and prevents the simulation from starting. I’m using GROMACS 2025.3 installed via conda-forge with CUDA support. The GPU is detected correctly and the software recognizes it, but fails when trying to compile the PTX kernels. The specific error is: “GPU kernel (k\_pruneonly) failed to launch: CUDA error #218 (cudaErrorInvalidPtx): a PTX JIT compilation failed.” **System configuration:** - GPU: NVIDIA RTX 5060 (Blackwell architecture, compute capability 12.0) - GROMACS: 2025.3-conda\_forge (nompi\_cuda build) - CUDA runtime: 12.60, Driver: 13.0 - Installation: `conda install conda-forge::gromacs=2025.3=nompi_cuda_h7ac747b_0` **What I’ve tried:** - Different GPU flag combinations (`-nb gpu -pme cpu`, `-nb gpu -pme auto`) - Cleaned CUDA cache (`rm -rf ~/.nv/`) - Verified the GPU works with other CUDA applications - The simulation runs fine in CPU-only mode **Specific questions:** 1. Has anyone successfully run GROMACS on RTX 5060 or other Blackwell GPUs? 2. Are there known issues with PTX JIT compilation on compute capability 12.0? 3. Should I try manual compilation with specific architecture flags? 4. Are there workarounds like environment variables or specific execution flags? 5. Does the conda-forge build properly support sm\_120 architecture? The full error occurs during the k\_pruneonly kernel launch. Any guidance would be greatly appreciated as I need to get this working for my research. Thank you for your help! this is the problem: * * * Program: gmx mdrun, version 2025.3-conda\_forge Source file: src/gromacs/gpu\_utils/cudautils.cuh (line 281) Function: launchGpuKernel\(void (_)(gmx::NBAtomDataGpu, gmx::NBParamGpu, gmx::GpuPairlist, int), const KernelLaunchConfig&, const DeviceStream&, CommandEvent_, const char\*, const std::array\&)::\ Assertion failed: Condition: stat == cudaSuccess GPU kernel (k\_pruneonly) failed to launch: CUDA error #218 (cudaErrorInvalidPtx): a PTX JIT compilation failed. ## ---
**Author:** ![al42and](https://dub1.discourse-cdn.com/flex017/user_avatar/gromacs.bioexcel.eu/al42and/32/1393_2.png) [@al42and](https://gromacs.bioexcel.eu/u/al42and)\ **Post date:** [September 26, 2025, 11:11am UTC](https://gromacs.bioexcel.eu/t/cuda-error-218/12691/2 "2025-09-26T11:11:02Z")
Hi, CUDA Runtime 12.6 does not support RTX5060. You need CUDA 12.8 or newer: [CUDA - Wikipedia](https://en.wikipedia.org/wiki/CUDA#GPUs_supported) Please build GROMACS yourself with an appropriate CUDA version (12.8, 12.9, or 13.0 all should work). To your specific questions: > Has anyone successfully run GROMACS on RTX 5060 or other Blackwell GPUs? Yes. > Are there known issues with PTX JIT compilation on compute capability 12.0? No. > Should I try manual compilation with specific architecture flags? The problem is with CUDA version, so manually specifying architecture flags would just result in a more clear error message. > Are there workarounds like environment variables or specific execution flags? No > Does the conda-forge build properly support sm\_120 architecture? Does not seem so. There is an open pull request enabling CUDA 13.0 for GROMACS Conda recipe ([Upgrade to CUDA 13.0 by regro-cf-autotick-bot · Pull Request #81 · conda-forge/gromacs-feedstock · GitHub](https://github.com/conda-forge/gromacs-feedstock/pull/81)), so it will hopefully be resolved in the future. ---
**Author:** ![Lgsus555](https://avatars.discourse-cdn.com/v4/letter/l/ad7895/32.png) [@Lgsus555](https://gromacs.bioexcel.eu/u/Lgsus555)\ **Post date:** [September 27, 2025, 7:59pm UTC](https://gromacs.bioexcel.eu/t/cuda-error-218/12691/3 "2025-09-27T19:59:39Z")
I already fixed it, the problem was that you have to install CUDA 13 and compile with DGMX\_CUDA\_TARGET\_SM=‘90;100;120’ -DGMX\_CUDA\_TARGET\_COMPUTE=‘90;100;120’ ---
**Author:** ![al42and](https://dub1.discourse-cdn.com/flex017/user_avatar/gromacs.bioexcel.eu/al42and/32/1393_2.png) [@al42and](https://gromacs.bioexcel.eu/u/al42and)\ **Post date:** [November 13, 2025, 6:24pm UTC](https://gromacs.bioexcel.eu/t/cuda-error-218/12691/4 "2025-11-13T18:24:24Z")
FYI, the conda-forge build of GROMACS 2025.3 was updated to use CUDA 12.9, so it should now work on Blackwell GPUs fine.