Skip to content

Commit 86d6298

Browse files
nv-guomingzdominicshanshan
authored andcommitted
[https://nvbugs/5468897][fix] fix invalid expression for disabling pa… (NVIDIA#7762)
Signed-off-by: nv-guomingz <[email protected]>
1 parent 833e86c commit 86d6298

File tree

1 file changed

+1
-1
lines changed

1 file changed

+1
-1
lines changed

tensorrt_llm/_torch/models/modeling_utils.py

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -895,7 +895,7 @@ def load_single_module(name, module):
895895
p.data.copy_(module_weights[n][:])
896896

897897
if os.environ.get("TRT_LLM_DISABLE_LOAD_WEIGHTS_IN_PARALLEL",
898-
True) in ["True", "true", "1", "yes", "y"]:
898+
"True") in ["True", "true", "1", "yes", "y"]:
899899
for name, module in tqdm(list(model.named_modules()),
900900
desc="Loading weights"):
901901
load_single_module(name, module)

0 commit comments

Comments
 (0)