Crash when using CUDA on Windows

[no1d]

I'm experimenting around with the server on Windows and it works fine using CPU.
But with CUDA it crashes after a client disconnects. Seems like the speech-to-text thread doesn't die properly.
In Event Viewer I see this:

Faulting application name: python.exe, version: 3.10.11150.1013, time stamp: 0x642cc427
Faulting module name: ucrtbase.dll, version: 10.0.26100.1882, time stamp: 0x52db7a2d
Exception code: 0xc0000409
Fault offset: 0x00000000000a502e

or

Faulting application name: python.exe, version: 3.10.11150.1013, time stamp: 0x642cc427
Faulting module name: KERNELBASE.dll, version: 10.0.26100.2454, time stamp: 0x398a1cce
Exception code: 0xe06d7363
Fault offset: 0x00000000000c837a

For CUDA I've used

pip install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cu124

Win11, 4070 SUPER, latest drivers

[xSlikZodiac]

I've had this issue too... it has been a MAJOR pain. running cuda 12.4 4080s

0xC0000409 (3221226505) = Windows’ stack buffer overrun.. ive literally tried to resolve on my own for the last year. @no1d if you get a solution PLEASE Share lol

[no1d]

It's a bug in CTranslate2, I've created a PR for it here OpenNMT/CTranslate2#1912

[xSlikZodiac]

okay thanks, ill comment there too. appreciate your fast response.

[xSlikZodiac]

@no1d just to confirm.. SYSTRAN/faster-whisper#71 (comment) this is what you did to fix the issue?

[no1d]

My patch is not merged yet.
This is the commit OpenNMT/CTranslate2@0968c24