Update vLLM-fork version to v0.7.2+Gaudi-1.21.0

Signed-off-by: CICD-at-OPEA <CICD@opea.dev>

.github/env/_build_image.sh

@@ -2,4 +2,4 @@
 # SPDX-License-Identifier: Apache-2.0
 
 export VLLM_VER=v0.8.3
-export VLLM_FORK_VER=v0.6.6.post1+Gaudi-1.20.0
+export VLLM_FORK_VER=v0.7.2+Gaudi-1.21.0

AgentQnA/tests/step1_build_images.sh

@@ -37,7 +37,7 @@ function build_agent_docker_image_gaudi_vllm() {
     get_genai_comps
 
     git clone https://github.com/HabanaAI/vllm-fork.git && cd vllm-fork
-    VLLM_FORK_VER=v0.6.6.post1+Gaudi-1.20.0
+    VLLM_FORK_VER=v0.7.2+Gaudi-1.21.0
     git checkout ${VLLM_FORK_VER} &> /dev/null && cd ../
 
     echo "Build agent image with --no-cache..."

AudioQnA/tests/test_compose_on_gaudi.sh

@@ -27,7 +27,7 @@ function build_docker_images() {
 
     git clone https://github.com/HabanaAI/vllm-fork.git
     cd vllm-fork/
-    VLLM_FORK_VER=v0.6.6.post1+Gaudi-1.20.0
+    VLLM_FORK_VER=v0.7.2+Gaudi-1.21.0
     echo "Check out vLLM tag ${VLLM_FORK_VER}"
     git checkout ${VLLM_FORK_VER} &> /dev/null && cd ../
 

ChatQnA/tests/test_compose_faqgen_on_gaudi.sh

@@ -24,7 +24,7 @@ function build_docker_images() {
     docker build --no-cache -t ${REGISTRY}/comps-base:${TAG} --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -f Dockerfile .
     popd && sleep 1s
     git clone https://github.com/HabanaAI/vllm-fork.git && cd vllm-fork
-    VLLM_FORK_VER=v0.6.6.post1+Gaudi-1.20.0
+    VLLM_FORK_VER=v0.7.2+Gaudi-1.21.0
     git checkout ${VLLM_FORK_VER} &> /dev/null && cd ../
 
     echo "Build all the images with --no-cache, check docker_image_build.log for details..."

ChatQnA/tests/test_compose_guardrails_on_gaudi.sh

@@ -24,7 +24,7 @@ function build_docker_images() {
     docker build --no-cache -t ${REGISTRY}/comps-base:${TAG} --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -f Dockerfile .
     popd && sleep 1s
     git clone https://github.com/HabanaAI/vllm-fork.git && cd vllm-fork
-    VLLM_FORK_VER=v0.6.6.post1+Gaudi-1.20.0
+    VLLM_FORK_VER=v0.7.2+Gaudi-1.21.0
     git checkout ${VLLM_FORK_VER} &> /dev/null && cd ../
 
     echo "Build all the images with --no-cache, check docker_image_build.log for details..."

ChatQnA/tests/test_compose_on_gaudi.sh

@@ -24,7 +24,7 @@ function build_docker_images() {
     docker build --no-cache -t ${REGISTRY}/comps-base:${TAG} --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -f Dockerfile .
     popd && sleep 1s
     git clone https://github.com/HabanaAI/vllm-fork.git && cd vllm-fork
-    VLLM_FORK_VER=v0.6.6.post1+Gaudi-1.20.0
+    VLLM_FORK_VER=v0.7.2+Gaudi-1.21.0
     git checkout ${VLLM_FORK_VER} &> /dev/null && cd ../
 
     echo "Build all the images with --no-cache, check docker_image_build.log for details..."

ChatQnA/tests/test_compose_without_rerank_on_gaudi.sh

@@ -24,7 +24,7 @@ function build_docker_images() {
     docker build --no-cache -t ${REGISTRY}/comps-base:${TAG} --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -f Dockerfile .
     popd && sleep 1s
     git clone https://github.com/HabanaAI/vllm-fork.git && cd vllm-fork
-    VLLM_FORK_VER=v0.6.6.post1+Gaudi-1.20.0
+    VLLM_FORK_VER=v0.7.2+Gaudi-1.21.0
     git checkout ${VLLM_FORK_VER} &> /dev/null && cd ../
 
     echo "Build all the images with --no-cache, check docker_image_build.log for details..."

CodeGen/tests/test_compose_on_gaudi.sh

@@ -37,7 +37,7 @@ function build_docker_images() {
 
     # Download Gaudi vllm of latest tag
     git clone https://github.com/HabanaAI/vllm-fork.git && cd vllm-fork
-    VLLM_FORK_VER=v0.6.6.post1+Gaudi-1.20.0
+    VLLM_FORK_VER=v0.7.2+Gaudi-1.21.0
     echo "Check out vLLM tag ${VLLM_FORK_VER}"
     git checkout ${VLLM_FORK_VER} &> /dev/null && cd ../
 

CodeTrans/tests/test_compose_on_gaudi.sh

@@ -26,7 +26,7 @@ function build_docker_images() {
     popd && sleep 1s
 
     git clone https://github.com/HabanaAI/vllm-fork.git && cd vllm-fork
-    VLLM_FORK_VER=v0.6.6.post1+Gaudi-1.20.0
+    VLLM_FORK_VER=v0.7.2+Gaudi-1.21.0
     git checkout ${VLLM_FORK_VER} &> /dev/null && cd ../
 
     echo "Build all the images with --no-cache, check docker_image_build.log for details..."

DocSum/tests/test_compose_on_gaudi.sh

@@ -50,7 +50,7 @@ function build_docker_images() {
     popd && sleep 1s
 
     git clone https://github.com/HabanaAI/vllm-fork.git && cd vllm-fork
-    VLLM_FORK_VER=v0.6.6.post1+Gaudi-1.20.0
+    VLLM_FORK_VER=v0.7.2+Gaudi-1.21.0
     git checkout ${VLLM_FORK_VER} &> /dev/null && cd ../
 
     echo "Build all the images with --no-cache, check docker_image_build.log for details..."

FinanceAgent/tests/test_compose_on_gaudi.sh

@@ -60,7 +60,7 @@ function build_vllm_docker_image() {
     fi
     cd ./vllm-fork
 
-    VLLM_FORK_VER=v0.6.6.post1+Gaudi-1.20.0
+    VLLM_FORK_VER=v0.7.2+Gaudi-1.21.0
     git checkout ${VLLM_FORK_VER} &> /dev/null
     docker build --no-cache -f Dockerfile.hpu -t $vllm_image --shm-size=128g . --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy
     if [ $? -ne 0 ]; then

VisualQnA/tests/test_compose_on_gaudi.sh

@@ -27,7 +27,7 @@ function build_docker_images() {
     popd && sleep 1s
 
     git clone https://github.com/HabanaAI/vllm-fork.git && cd vllm-fork
-    VLLM_FORK_VER=v0.6.6.post1+Gaudi-1.20.0
+    VLLM_FORK_VER=v0.7.2+Gaudi-1.21.0
     git checkout ${VLLM_FORK_VER} &> /dev/null && cd ../
 
     service_list="visualqna visualqna-ui lvm nginx vllm-gaudi"