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 3, 11:45 UTC
[MRV2][XPU] add Model Runner V2 log (#42710)
Signed-off-by: zhenwei-intel <zhenwei.liu@intel.com>
liuzhenwei committed
May 17, 2026 at 12:15 UTC
ff712f6447093d07747c88680b9d006b119f5890
1 file changed
+3
vllm/v1/worker/xpu_worker.py
+3
@@ -104,6 +104,9 @@ class XPUWorker(Worker):
104
if torch.distributed.is_xccl_available():
105
torch.distributed.all_reduce(torch.zeros(1).xpu())
106
107
+ if self.use_v2_model_runner:
108
+ logger.info_once("Using V2 Model Runner")
109
+
110
# Set random seed.
111
set_random_seed(self.model_config.seed)
112