Memory allocation error under stress
Closed this issue · 0 comments
jug-dev commented
TRACE | 2023-05-14 19:13:37.730978 | worker.jobs.stable_diffusion:start_job:237 - Traceback (most recent call last):
File "F:\AI\dev\AI-Horde-Worker\worker\jobs\stable_diffusion.py", line 216, in start_job
self.image = generator(gen_payload)
File "F:\AI\dev\AI-Horde-Worker\conda\envs\windows\lib\site-packages\hordelib\horde.py", line 452, in basic_inference
images = self.generator.run_image_pipeline(pipeline, params)
File "F:\AI\dev\AI-Horde-Worker\conda\envs\windows\lib\site-packages\hordelib\comfy_horde.py", line 542, in run_image_pipeline
result = self.run_pipeline(pipeline_name, params)
File "F:\AI\dev\AI-Horde-Worker\conda\envs\windows\lib\site-packages\hordelib\comfy_horde.py", line 513, in run_pipeline
cleanup()
File "F:\AI\dev\AI-Horde-Worker\conda\envs\windows\lib\site-packages\hordelib\comfy_horde.py", line 60, in cleanup
unload_model_from_gpu(model_data["model"])
File "F:\AI\dev\AI-Horde-Worker\conda\envs\windows\lib\site-packages\hordelib\comfy_horde.py", line 100, in unload_model_from_gpu
_comfy_model_manager.load_model_gpu(model)
File "F:\AI\dev\AI-Horde-Worker\conda\envs\windows\lib\site-packages\hordelib\_comfyui\comfy\model_management.py", line 198, in load_model_gpu
if self.unload_model(release_model):
File "F:\AI\dev\AI-Horde-Worker\conda\envs\windows\lib\site-packages\hordelib\_comfyui\comfy\model_management.py", line 173, in unload_model
model.model.cpu()
File "F:\AI\dev\AI-Horde-Worker\conda\envs\windows\lib\site-packages\torch\nn\modules\module.py", line 954, in cpu
return self._apply(lambda t: t.cpu())
File "F:\AI\dev\AI-Horde-Worker\conda\envs\windows\lib\site-packages\torch\nn\modules\module.py", line 797, in _apply
module._apply(fn)
File "F:\AI\dev\AI-Horde-Worker\conda\envs\windows\lib\site-packages\torch\nn\modules\module.py", line 797, in _apply
module._apply(fn)
File "F:\AI\dev\AI-Horde-Worker\conda\envs\windows\lib\site-packages\torch\nn\modules\module.py", line 797, in _apply
module._apply(fn)
[Previous line repeated 7 more times]
File "F:\AI\dev\AI-Horde-Worker\conda\envs\windows\lib\site-packages\torch\nn\modules\module.py", line 820, in _apply
param_applied = fn(param)
File "F:\AI\dev\AI-Horde-Worker\conda\envs\windows\lib\site-packages\torch\nn\modules\module.py", line 954, in <lambda>
return self._apply(lambda t: t.cpu())
RuntimeError: [enforce fail at ..\c10\core\impl\alloc_cpu.cpp:72] data. DefaultCPUAllocator: not enough memory: you tried to allocate 3276800 bytes.