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, 07:00 UTC
[Bugfix] Ignore ray reinit error when current platform is ROCm or XPU (#10375)
Signed-off-by: Hollow Man <hollowman@opensuse.org>
ℍ𝕠𝕝𝕝𝕠𝕨 𝕄𝕒𝕟 committed
Nov 18, 2024 at 05:29 UTC
47826cacf0e037b4e109f0b2d8d594e47def500e
1 file changed
+1
-1
vllm/executor/ray_utils.py
+1
-1
@@ -234,7 +234,7 @@ def initialize_ray_cluster(
234
if current_platform.is_rocm() or current_platform.is_xpu():
235
# Try to connect existing ray instance and create a new one if not found
236
try:
237
- ray.init("auto")
237
+ ray.init("auto", ignore_reinit_error=True)
238
except ConnectionError:
239
logger.warning(
240
"No existing RAY instance detected. "