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 16, 03:15 UTC
[ci] fix gh200 tests (#11919)
Signed-off-by: youkaichao <youkaichao@gmail.com>
youkaichao committed
Jan 10, 2025 at 16:25 UTC
d53575a5f0e5c0f9003b4ec6e33c8bf761e93cef
1 file changed
+3
-1
vllm/model_executor/model_loader/weight_utils.py
+3
-1
@@ -29,7 +29,9 @@ from vllm.utils import PlaceholderModule
29
30
try:
31
from runai_model_streamer import SafetensorsStreamer
32
-except ImportError:
32
+except (ImportError, OSError):
33
+ # see https://github.com/run-ai/runai-model-streamer/issues/26
34
+ # OSError will be raised on arm64 platform
35
runai_model_streamer = PlaceholderModule(
36
"runai_model_streamer") # type: ignore[assignment]
37
SafetensorsStreamer = runai_model_streamer.placeholder_attr(