fix rebase

Signed-off-by: Yuan Zhou <yuan.zhou@intel.com>

Author: zhouyuan

.buildkite/run-cpu-test.sh

@@ -21,4 +21,4 @@ docker exec cpu-test bash -c "cd tests;
   pip install pytest Pillow protobuf
   bash ../.buildkite/download-images.sh
   cd ../
-  pytest -v -s tests/models --ignore=tests/models/test_llava.py --ignore=tests/models/test_embedding.py"
+  pytest -v -s tests/models --ignore=tests/models/test_llava.py --ignore=tests/models/test_embedding.py --ignore=tests/models/test_registry.py"

Dockerfile.cpu

@@ -1,6 +1,6 @@
 # This vLLM Dockerfile is used to construct image that can build and run vLLM on x86 CPU platform.
 
-FROM ubuntu:22.04
+FROM ubuntu:22.04 AS cpu-test-1
 
 RUN apt-get update  -y \
     && apt-get install -y git wget vim numactl gcc-12 g++-12 python3 python3-pip \
@@ -9,6 +9,8 @@ RUN apt-get update  -y \
 RUN pip install --upgrade pip \
     && pip install wheel packaging ninja setuptools>=49.4.0 numpy
 
+FROM cpu-test-1 AS build
+
 COPY ./ /workspace/vllm
 
 WORKDIR /workspace/vllm

tests/conftest.py

@@ -146,9 +146,9 @@ class HfRunner:
 
     def wrap_device(self, input: any):
         if not is_cpu():
-            return input.cuda()
+            return input.to("cuda")
         else:
-            return input.cpu()
+            return input.to("cpu")
 
     def __init__(
         self,