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
[platforms] restore xpu check for parallel config (#10479)
Signed-off-by: youkaichao <youkaichao@gmail.com>
youkaichao committed
Nov 20, 2024 at 09:13 UTC
772a66732d0ff58a43dbd1ae79c0d165659aa96d
1 file changed
+10
vllm/platforms/xpu.py
+10
@@ -55,3 +55,13 @@ class XPUPlatform(Platform):
55
"CUDA graph is not supported on XPU, fallback to the eager "
56
"mode.")
57
model_config.enforce_eager = True
58
+
59
+ # check and update parallel config
60
+ parallel_config = vllm_config.parallel_config
61
+ if (parallel_config.distributed_executor_backend is not None
62
+ and parallel_config.distributed_executor_backend != "ray"):
63
+ logger.warning(
64
+ "%s is not supported on XPU, fallback to ray distributed"
65
+ " executor backend.",
66
+ parallel_config.distributed_executor_backend)
67
+ parallel_config.distributed_executor_backend = "ray"