mirror of
https://github.com/huggingface/text-generation-inference.git
synced 2025-04-24 08:22:07 +00:00
Attempting to fix torch leak.
This commit is contained in:
parent
a2a913eec5
commit
89a4e723d2
@ -659,6 +659,7 @@ class CausalLM(Model):
|
||||
|
||||
# We finished all generations in the batch; there is no next batch
|
||||
if stopped:
|
||||
torch.cuda.empty_cache()
|
||||
return generations, None
|
||||
|
||||
# Slice unused values from prefill
|
||||
|
Loading…
Reference in New Issue
Block a user