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, 05:30 UTC
[misc] Remove outdate comment about runai_model_streamer (#23421)
Signed-off-by: carlory <baofa.fan@daocloud.io>
杨朱 · Kiki committed
Aug 22, 2025 at 21:08 UTC
695e7adcd22c25b859a6d4b3af99617aaf425708
1 file changed
+1
-3
vllm/model_executor/model_loader/weight_utils.py
+1
-3
@@ -31,9 +31,7 @@ from vllm.utils import PlaceholderModule
31
32
try:
33
from runai_model_streamer import SafetensorsStreamer
34
-except (ImportError, OSError):
35
- # see https://github.com/run-ai/runai-model-streamer/issues/26
36
- # OSError will be raised on arm64 platform
34
+except ImportError:
35
runai_model_streamer = PlaceholderModule(
36
"runai_model_streamer") # type: ignore[assignment]
37
SafetensorsStreamer = runai_model_streamer.placeholder_attr(