# 🤨 RuntimeError: CUDA error: the launch timed out and was terminated **URL:** \ **Category:** Beginners\ **Created:** [October 1, 2023, 5:27am UTC](https://discuss.huggingface.co/t/runtimeerror-cuda-error-the-launch-timed-out-and-was-terminated/56976 "2023-10-01T05:27:29Z")\ **Posts on this page:** 2\ **Page:** 1
**Author:** ![gggdddrrr](https://sea2.discourse-cdn.com/hellohellohello/user_avatar/discuss.huggingface.co/gggdddrrr/32/19966_2.png) [@gggdddrrr](https://discuss.huggingface.co/u/gggdddrrr)\ **Post date:** [October 1, 2023, 5:27am UTC](https://discuss.huggingface.co/t/runtimeerror-cuda-error-the-launch-timed-out-and-was-terminated/56976/1 "2023-10-01T05:27:29Z")
Hello 🙂 It’s been several weeks since I encountered an error with Stable Diffusion on my computer (HP Z2 Mini, 16 GB of RAM). Since I updated stable diffusion with Automatic 1111, I have a “CUDA” error which prevents me from making large images (whereas before, everything worked fine). here is the detail of this error, I hope to find some help, thank you so much Geoffrey * * * Traceback (most recent call last): File “C:\Program Files\WindowsApps\PythonSoftwareFoundation.Python.3.10\_3.10.3056.0\_x64\_\_qbz5n2kfra8p0\lib\threading.py”, line 1016, in \_bootstrap\_inner self.run() File “C:\Users\G\stable-diffusion-webui\modules\memmon.py”, line 53, in run free, total = self.cuda\_mem\_get\_info() File “C:\Users\G\stable-diffusion-webui\modules\memmon.py”, line 34, in cuda\_mem\_get\_info return torch.cuda.mem\_get\_info(index) File “C:\Users\G\stable-diffusion-webui\venv\lib\site-packages\torch\cuda\memory.py”, line 618, in mem\_get\_info \*\*\* Error completing request \*\*\* Arguments: (‘task(m3u61mpj738zl2g)’, ‘photo of a 30 year old German, worker, lora:epiNoiseoffset\_v2:1 lora:add\_detail:0.8’, ‘disfigured, ugly, deformed, blur’, , 27, ‘DPM++ 2M SDE Karras’, 1, 1, 7, 800, 400, False, 0.7, 2, ‘Latent’, 0, 0, 0, ‘Use same checkpoint’, ‘Use same sampler’, ‘’, ‘’, , \, 0, False, ‘’, 0.8, False, -1, 0, 0, 0, True, False, False, ‘positive’, ‘comma’, 0, False, False, ‘’, 1, ‘’, , 0, ‘’, , 0, ‘’, , True, False, False, False, 0, False) {} return torch.cuda.cudart().cudaMemGetInfo(device) RuntimeError: CUDA error: the launch timed out and was terminated 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 with `TORCH_USE_CUDA_DSA` to enable device-side assertions. ``` Traceback (most recent call last): File "C:\Users\G\stable-diffusion-webui\modules\call_queue.py", line 57, in f res = list(func(*args, **kwargs)) File "C:\Users\G\stable-diffusion-webui\modules\call_queue.py", line 36, in f res = func(*args, **kwargs) File "C:\Users\G\stable-diffusion-webui\modules\txt2img.py", line 55, in txt2img processed = processing.process_images(p) File "C:\Users\G\stable-diffusion-webui\modules\processing.py", line 732, in process_images res = process_images_inner(p) File "C:\Users\G\stable-diffusion-webui\modules\processing.py", line 875, in process_images_inner x_samples_ddim = decode_latent_batch(p.sd_model, samples_ddim, target_device=devices.cpu, check_for_nans=True) File "C:\Users\G\stable-diffusion-webui\modules\processing.py", line 598, in decode_latent_batch devices.test_for_nans(sample, "vae") File "C:\Users\G\stable-diffusion-webui\modules\devices.py", line 117, in test_for_nans if not torch.all(torch.isnan(x)).item(): RuntimeError: CUDA error: the launch timed out and was terminated 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 with `TORCH_USE_CUDA_DSA` to enable device-side assertions. ``` * * * Traceback (most recent call last): File “C:\Users\G\stable-diffusion-webui\venv\lib\site-packages\gradio\routes.py”, line 488, in run\_predict output = await app.get\_blocks().process\_api( File “C:\Users\G\stable-diffusion-webui\venv\lib\site-packages\gradio\blocks.py”, line 1431, in process\_api result = await self.call\_function( File “C:\Users\G\stable-diffusion-webui\venv\lib\site-packages\gradio\blocks.py”, line 1103, in call\_function prediction = await anyio.to\_thread.run\_sync( File “C:\Users\G\stable-diffusion-webui\venv\lib\site-packages\anyio\to\_thread.py”, line 33, in run\_sync return await get\_asynclib().run\_sync\_in\_worker\_thread( File “C:\Users\G\stable-diffusion-webui\venv\lib\site-packages\anyio\_backends\_asyncio.py”, line 877, in run\_sync\_in\_worker\_thread return await future File “C:\Users\G\stable-diffusion-webui\venv\lib\site-packages\anyio\_backends\_asyncio.py”, line 807, in run result = context.run(func, \*args) File “C:\Users\G\stable-diffusion-webui\venv\lib\site-packages\gradio\utils.py”, line 707, in wrapper response = f(\*args, \*\*kwargs) File “C:\Users\G\stable-diffusion-webui\modules\call\_queue.py”, line 77, in f devices.torch\_gc() File “C:\Users\G\stable-diffusion-webui\modules\devices.py”, line 51, in torch\_gc torch.cuda.empty\_cache() File “C:\Users\G\stable-diffusion-webui\venv\lib\site-packages\torch\cuda\memory.py”, line 133, in empty\_cache torch.\_C.\_cuda\_emptyCache() RuntimeError: CUDA error: the launch timed out and was terminated 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 with `TORCH_USE_CUDA_DSA` to enable device-side assertions. ---
**Author:** ![mtrabado](https://avatars.discourse-cdn.com/v4/letter/m/58956e/32.png) [@mtrabado](https://discuss.huggingface.co/u/mtrabado)\ **Post date:** [October 23, 2023, 7:33am UTC](https://discuss.huggingface.co/t/runtimeerror-cuda-error-the-launch-timed-out-and-was-terminated/56976/2 "2023-10-23T07:33:17Z")
Hi. I am facing a similar issue. Did you find any solution? Thanks in advance 🙂