Upgrade vllm to v0.17.0 (#3006)

Author: xyang16

serving/docker/lmi-container-requirements.txt

@@ -1,12 +1,12 @@
-torch==2.9.1
+torch==2.10.0
 transformers >= 4.56.0, < 5
 huggingface-hub
 hf-transfer
-peft==0.15.1
-sentence-transformers==3.3.1
-optimum==1.23.2
-llmcompressor==0.9.0.1
-mpi4py==4.0.1
-https://djl-ai.s3.us-east-1.amazonaws.com/publish/vllm/vllm-0.16.1.dev6%2Bg369fca226-cp312-cp312-linux_x86_64.whl
-lmcache
-autoawq
+peft==0.18.1
+sentence-transformers==5.2.3
+optimum==2.1.0
+mpi4py==4.1.1
+compressed-tensors==0.13.0
+https://wheels.vllm.ai/dc6b57846686206d6d77fe788f71ab7fe8e568ab/vllm-0.17.0rc1.dev168%2Bgdc6b57846-cp38-abi3-manylinux_2_31_x86_64.whl
+autoawq==0.2.9
+https://publish.djl.ai/lmcache/lmcache-0.3.16.dev0-cp312-cp312-linux_x86_64.whl

serving/docker/lmi.Dockerfile

@@ -90,7 +90,7 @@ RUN scripts/patch_oss_dlc.sh python \
 
 COPY lmi-container-requirements.txt ./requirements.txt
 RUN pip3 install --upgrade pip setuptools
-RUN pip3 install torch==2.9.1 torchvision --index-url https://download.pytorch.org/whl/cu129 \
+RUN pip3 install torch==2.10.0 torchvision --index-url https://download.pytorch.org/whl/${cuda_version} \
     && pip3 install -r requirements.txt \
     && pip3 install ${djl_converter_wheel} --no-deps
 
@@ -105,7 +105,7 @@ RUN scripts/install_djl_serving.sh $djl_version $djl_serving_version \
 LABEL maintainer="djl-dev@amazon.com"
 LABEL dlc_major_version="1"
 LABEL com.amazonaws.ml.engines.sagemaker.dlc.framework.djl.lmi="true"
-LABEL com.amazonaws.ml.engines.sagemaker.dlc.framework.djl.v0-34-0.lmi="true"
+LABEL com.amazonaws.ml.engines.sagemaker.dlc.framework.djl.v0-36-0.lmi="true"
 LABEL com.amazonaws.sagemaker.capabilities.multi-models="true"
 LABEL com.amazonaws.sagemaker.capabilities.accept-bind-to-port="true"
 LABEL djl-version=$djl_version