A high-throughput and memory-efficient inference and serving engine for LLMs
Mirrored from https://github.com/tduncan-lum/Nvidia-Optimization-Stack---VLLM.git
Synced Nov 14, 23:45 UTC
[Bugfix] fix max-file-size type from str to int (#21675)
Signed-off-by: Andy Xie <andy.xning@gmail.com>
Ning Xie committed
Jul 28, 2025 at 15:06 UTC
150d9e6337c2dcfe06d97b0213fddeeb85ba4487
1 file changed
+1
-1
examples/offline_inference/save_sharded_state.py
+1
-1
@@ -47,7 +47,7 @@ def parse_args():
47
)
48
parser.add_argument(
49
"--max-file-size",
50
- type=str,
50
+ type=int,
51
default=5 * 1024**3,
52
help="max size (in bytes) of each safetensors file",
53
)