mirror of
https://github.com/oobabooga/text-generation-webui.git
synced 2024-11-22 08:07:56 +01:00
Gracefully handle CUDA out of memory errors with streaming
This commit is contained in:
parent
b2f356a9ae
commit
304f812c63
@ -1,4 +1,5 @@
|
|||||||
import gc
|
import gc
|
||||||
|
import traceback
|
||||||
from queue import Queue
|
from queue import Queue
|
||||||
from threading import Thread
|
from threading import Thread
|
||||||
|
|
||||||
@ -63,6 +64,10 @@ class Iteratorize:
|
|||||||
ret = self.mfunc(callback=_callback, **self.kwargs)
|
ret = self.mfunc(callback=_callback, **self.kwargs)
|
||||||
except ValueError:
|
except ValueError:
|
||||||
pass
|
pass
|
||||||
|
except:
|
||||||
|
traceback.print_exc()
|
||||||
|
pass
|
||||||
|
|
||||||
clear_torch_cache()
|
clear_torch_cache()
|
||||||
self.q.put(self.sentinel)
|
self.q.put(self.sentinel)
|
||||||
if self.c_callback:
|
if self.c_callback:
|
||||||
|
Loading…
Reference in New Issue
Block a user