Skip to content

Fix vllm version issue #2012

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
wants to merge 8 commits into
base: main
Choose a base branch
from
Open

Fix vllm version issue #2012

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
8 commits
Select commit Hold shift + click to select a range
8ba40a5
Update vLLM-fork version to v0.7.2+Gaudi-1.21.0
CICD-at-OPEA May 8, 2025
46fab4a
Merge branch 'main' into update_vLLM-fork
xiguiw May 16, 2025
66ecaf2
Merge branch 'main' into update_vLLM-fork
chensuyue May 20, 2025
c712c01
Update vLLM-fork version to v0.7.2+Gaudi-1.21.0
CICD-at-OPEA May 20, 2025
2291d19
Merge branch 'main' into update_vLLM-fork
chensuyue May 28, 2025
7cb7e33
Increase the warm-up time of vLLM.
WenjiaoYue May 30, 2025
3075bac
Merge branch 'main' into wenjiao/fix_vllm_version_issue
WenjiaoYue May 30, 2025
3dccd77
Merge branch 'main' into wenjiao/fix_vllm_version_issue
WenjiaoYue Jun 4, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion .github/env/_build_image.sh
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -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
4 changes: 2 additions & 2 deletions AgentQnA/docker_compose/intel/hpu/gaudi/compose.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -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:
Expand Down
2 changes: 1 addition & 1 deletion AgentQnA/tests/step1_build_images.sh
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -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..."
Expand Down
4 changes: 2 additions & 2 deletions AudioQnA/docker_compose/intel/hpu/gaudi/compose.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -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:
Expand Down
2 changes: 1 addition & 1 deletion AudioQnA/tests/test_compose_on_gaudi.sh
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -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 ../

Expand Down
4 changes: 2 additions & 2 deletions ChatQnA/docker_compose/intel/hpu/gaudi/compose.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -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:
Expand Down
4 changes: 2 additions & 2 deletions ChatQnA/docker_compose/intel/hpu/gaudi/compose_guardrails.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -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}
Expand Down
2 changes: 1 addition & 1 deletion ChatQnA/tests/test_compose_faqgen_on_gaudi.sh
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -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..."
Expand Down
2 changes: 1 addition & 1 deletion ChatQnA/tests/test_compose_guardrails_on_gaudi.sh
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -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..."
Expand Down
2 changes: 1 addition & 1 deletion ChatQnA/tests/test_compose_on_gaudi.sh
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -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..."
Expand Down
2 changes: 1 addition & 1 deletion ChatQnA/tests/test_compose_without_rerank_on_gaudi.sh
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -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..."
Expand Down
4 changes: 2 additions & 2 deletions CodeGen/docker_compose/intel/hpu/gaudi/compose.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -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:
Expand Down
2 changes: 1 addition & 1 deletion CodeGen/tests/test_compose_on_gaudi.sh
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -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 ../

Expand Down
4 changes: 2 additions & 2 deletions CodeTrans/docker_compose/intel/hpu/gaudi/compose.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -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:
Expand Down
2 changes: 1 addition & 1 deletion CodeTrans/tests/test_compose_on_gaudi.sh
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -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..."
Expand Down
4 changes: 2 additions & 2 deletions DocSum/docker_compose/intel/hpu/gaudi/compose.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -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:
Expand Down
2 changes: 1 addition & 1 deletion DocSum/tests/test_compose_on_gaudi.sh
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -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..."
Expand Down
2 changes: 1 addition & 1 deletion FinanceAgent/tests/test_compose_on_gaudi.sh
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -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
Expand Down
2 changes: 1 addition & 1 deletion VisualQnA/tests/test_compose_on_gaudi.sh
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -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"
Expand Down
Loading