Repository navigation
CUDA Error: cudaErrorNoKernelImageForDevice during generation #395
Description
I am encountering a runtime error when attempting to run the generation script for Voicebox. The process fails immediately with a CUDA kernel image error, suggesting a mismatch between the compiled binaries and my GPU hardware.
Error
Generation failed
CUDA error: no kernel image is available for
execution on the device Search for
cudaErrorNoKernellmageForDevice' in https://docs.nvidia.com/cuda/cuda-runtime- api/group_CUDART_TYPES.html for more information. CUDA kernel errors might be asynchronously reported at some other API call, so the stacktrace below might be incorrect. For debugging consider passing CUDA_LAUNCH_BLOCKING=1 Compile withTORCH_USE_CUDA_DSA` to enable device-side
assertions.
- Gpu: 5060ti 16gb
- Driver: 595.97
- OS: Win 11
Activity
thackeba commentedon Apr 11, 2026
I have been having the same issue with my 5090 as well.
feat: add Blackwell GPU (sm_120) CUDA support
duquevazzaro commentedon Apr 13, 2026
I've compiled a version that includes CUDA support for the RTX 50 Series. I have an RTX 5080, and it works perfectly. If anyone's interested, I'll upload the release to my GitHub so you can try it out and give me some feedback.
platinumturtle commentedon Apr 13, 2026
I'm having the same problem but using a RTX 5070 Ti, @duquevazzaro maybe your version could be our solution to this issue
duquevazzaro commentedon Apr 14, 2026
I'll get right on it. I'll let you know when the source code and the release are uploaded to my Git :)
Jhonatanjhs commentedon Apr 14, 2026
Nice! That'd be great
feat: add Blackwell GPU (sm_120) CUDA support (#401)
duquevazzaro commentedon Apr 16, 2026
Ready guys https://github.com/duquevazzaro/clonvoice-releases/tree/main
Buy me a coffee :)
capy-ai-staging commentedon Oct 7, 2026
This was fixed by #316 and #401 (thanks @mvanhorn): the Windows CUDA backend moved from cu126 to cu128 wheels with sm_120 in the build, so RTX 50-series (Blackwell) cards have worked since Voicebox 0.4.0. If you are still on 0.3.x, please update and re-download the CUDA backend from Settings. Closing as fixed; if you still hit "no kernel image is available" on 0.4.0 or later, please reopen with the log.