diff --git a/.github/env/_build_image.sh b/.github/env/_build_image.sh
index d559137fed..d21c4d76ea 100644
--- a/.github/env/_build_image.sh
+++ b/.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
diff --git a/AgentQnA/docker_compose/intel/hpu/gaudi/compose.yaml b/AgentQnA/docker_compose/intel/hpu/gaudi/compose.yaml
index a5240ad4b8..1c6d40d243 100644
--- a/AgentQnA/docker_compose/intel/hpu/gaudi/compose.yaml
+++ b/AgentQnA/docker_compose/intel/hpu/gaudi/compose.yaml
@@ -131,8 +131,8 @@ services:
       PT_HPU_ENABLE_LAZY_COLLECTIVES: true
     healthcheck:
       test: ["CMD-SHELL", "curl -f http://$host_ip:8086/health || exit 1"]
-      interval: 10s
-      timeout: 10s
+      interval: 100s
+      timeout: 100s
       retries: 100
     runtime: habana
     cap_add:
diff --git a/AgentQnA/tests/step1_build_images.sh b/AgentQnA/tests/step1_build_images.sh
index 58b5c8d6e8..11fe7963db 100644
--- a/AgentQnA/tests/step1_build_images.sh
+++ b/AgentQnA/tests/step1_build_images.sh
@@ -41,7 +41,7 @@ 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..."
diff --git a/AudioQnA/docker_compose/intel/hpu/gaudi/compose.yaml b/AudioQnA/docker_compose/intel/hpu/gaudi/compose.yaml
index c1e9db4505..b24ee5278f 100644
--- a/AudioQnA/docker_compose/intel/hpu/gaudi/compose.yaml
+++ b/AudioQnA/docker_compose/intel/hpu/gaudi/compose.yaml
@@ -55,8 +55,8 @@ services:
       LLM_SERVER_PORT: ${LLM_SERVER_PORT}
     healthcheck:
       test: ["CMD-SHELL", "curl -f http://$host_ip:${LLM_SERVER_PORT}/health || exit 1"]
-      interval: 10s
-      timeout: 10s
+      interval: 100s
+      timeout: 100s
       retries: 100
     runtime: habana
     cap_add:
diff --git a/AudioQnA/tests/test_compose_on_gaudi.sh b/AudioQnA/tests/test_compose_on_gaudi.sh
index c24f5ff82e..746c6a77e5 100644
--- a/AudioQnA/tests/test_compose_on_gaudi.sh
+++ b/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 ../
 
diff --git a/ChatQnA/docker_compose/intel/hpu/gaudi/compose.yaml b/ChatQnA/docker_compose/intel/hpu/gaudi/compose.yaml
index 49d7ff99a5..cd36d095c7 100644
--- a/ChatQnA/docker_compose/intel/hpu/gaudi/compose.yaml
+++ b/ChatQnA/docker_compose/intel/hpu/gaudi/compose.yaml
@@ -109,8 +109,8 @@ services:
       VLLM_TORCH_PROFILER_DIR: "/mnt"
     healthcheck:
       test: ["CMD-SHELL", "curl -f http://localhost:80/health || exit 1"]
-      interval: 10s
-      timeout: 10s
+      interval: 100s
+      timeout: 100s
       retries: 100
     runtime: habana
     cap_add:
diff --git a/ChatQnA/docker_compose/intel/hpu/gaudi/compose_guardrails.yaml b/ChatQnA/docker_compose/intel/hpu/gaudi/compose_guardrails.yaml
index 7f44764413..e5f9a1cb4b 100644
--- a/ChatQnA/docker_compose/intel/hpu/gaudi/compose_guardrails.yaml
+++ b/ChatQnA/docker_compose/intel/hpu/gaudi/compose_guardrails.yaml
@@ -55,8 +55,8 @@ services:
     command: --model ${GURADRAILS_MODEL_ID} --tensor-parallel-size ${NUM_CARDS} --host 0.0.0.0 --port 80 --block-size 128 --max-num-seqs 256 --max-seq-len-to-capture 2048
     healthcheck:
       test: ["CMD-SHELL", "curl -f http://$host_ip:8088/health || exit 1"]
-      interval: 10s
-      timeout: 10s
+      interval: 100s
+      timeout: 100s
       retries: 150
   guardrails:
     image: ${REGISTRY:-opea}/guardrails:${TAG:-latest}
diff --git a/ChatQnA/tests/test_compose_faqgen_on_gaudi.sh b/ChatQnA/tests/test_compose_faqgen_on_gaudi.sh
index fc95182346..336aea7608 100644
--- a/ChatQnA/tests/test_compose_faqgen_on_gaudi.sh
+++ b/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..."
diff --git a/ChatQnA/tests/test_compose_guardrails_on_gaudi.sh b/ChatQnA/tests/test_compose_guardrails_on_gaudi.sh
index c24a0c537f..dc75b0034c 100644
--- a/ChatQnA/tests/test_compose_guardrails_on_gaudi.sh
+++ b/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..."
diff --git a/ChatQnA/tests/test_compose_on_gaudi.sh b/ChatQnA/tests/test_compose_on_gaudi.sh
index 857d25ce05..a84966d032 100644
--- a/ChatQnA/tests/test_compose_on_gaudi.sh
+++ b/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..."
diff --git a/ChatQnA/tests/test_compose_without_rerank_on_gaudi.sh b/ChatQnA/tests/test_compose_without_rerank_on_gaudi.sh
index a1ee6922c0..5dd05a78f7 100644
--- a/ChatQnA/tests/test_compose_without_rerank_on_gaudi.sh
+++ b/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..."
diff --git a/CodeGen/docker_compose/intel/hpu/gaudi/compose.yaml b/CodeGen/docker_compose/intel/hpu/gaudi/compose.yaml
index fb9a78d252..b2b969c793 100644
--- a/CodeGen/docker_compose/intel/hpu/gaudi/compose.yaml
+++ b/CodeGen/docker_compose/intel/hpu/gaudi/compose.yaml
@@ -54,8 +54,8 @@ services:
       VLLM_TORCH_PROFILER_DIR: "/mnt"
     healthcheck:
       test: ["CMD-SHELL", "curl -f http://localhost:80/health || exit 1"]
-      interval: 10s
-      timeout: 10s
+      interval: 100s
+      timeout: 100s
       retries: 100
     runtime: habana
     cap_add:
diff --git a/CodeGen/tests/test_compose_on_gaudi.sh b/CodeGen/tests/test_compose_on_gaudi.sh
index 38354233d9..db4a741301 100644
--- a/CodeGen/tests/test_compose_on_gaudi.sh
+++ b/CodeGen/tests/test_compose_on_gaudi.sh
@@ -27,7 +27,7 @@ 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 ../
 
diff --git a/CodeTrans/docker_compose/intel/hpu/gaudi/compose.yaml b/CodeTrans/docker_compose/intel/hpu/gaudi/compose.yaml
index f34fe5a1e4..a8de5bdefa 100644
--- a/CodeTrans/docker_compose/intel/hpu/gaudi/compose.yaml
+++ b/CodeTrans/docker_compose/intel/hpu/gaudi/compose.yaml
@@ -21,8 +21,8 @@ services:
       VLLM_TORCH_PROFILER_DIR: "/mnt"
     healthcheck:
       test: ["CMD-SHELL", "curl -f http://$host_ip:8008/health || exit 1"]
-      interval: 10s
-      timeout: 10s
+      interval: 100s
+      timeout: 100s
       retries: 100
     runtime: habana
     cap_add:
diff --git a/CodeTrans/tests/test_compose_on_gaudi.sh b/CodeTrans/tests/test_compose_on_gaudi.sh
index 600c20a0c3..0d4ed72268 100644
--- a/CodeTrans/tests/test_compose_on_gaudi.sh
+++ b/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..."
diff --git a/DocSum/docker_compose/intel/hpu/gaudi/compose.yaml b/DocSum/docker_compose/intel/hpu/gaudi/compose.yaml
index 2efa09e890..3d5213c481 100644
--- a/DocSum/docker_compose/intel/hpu/gaudi/compose.yaml
+++ b/DocSum/docker_compose/intel/hpu/gaudi/compose.yaml
@@ -22,8 +22,8 @@ services:
       VLLM_TORCH_PROFILER_DIR: "/mnt"
     healthcheck:
       test: ["CMD-SHELL", "curl -f http://localhost:80/health || exit 1"]
-      interval: 10s
-      timeout: 10s
+      interval: 100s
+      timeout: 100s
       retries: 100
     runtime: habana
     cap_add:
diff --git a/DocSum/tests/test_compose_on_gaudi.sh b/DocSum/tests/test_compose_on_gaudi.sh
index a75a16c5d4..1f1e9da9dd 100644
--- a/DocSum/tests/test_compose_on_gaudi.sh
+++ b/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..."
diff --git a/FinanceAgent/tests/test_compose_on_gaudi.sh b/FinanceAgent/tests/test_compose_on_gaudi.sh
index d534ffa122..016d290c6b 100644
--- a/FinanceAgent/tests/test_compose_on_gaudi.sh
+++ b/FinanceAgent/tests/test_compose_on_gaudi.sh
@@ -96,7 +96,7 @@ 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
diff --git a/VisualQnA/tests/test_compose_on_gaudi.sh b/VisualQnA/tests/test_compose_on_gaudi.sh
index 1df520183c..757103f9a8 100644
--- a/VisualQnA/tests/test_compose_on_gaudi.sh
+++ b/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"