Skip to content

Update vllm-ipex, boost serving performance #1941

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

Merged
ZePan110 merged 1 commit into from
Nov 17, 2025
Merged

Update vllm-ipex, boost serving performance #1941

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
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 comps/llms/deployment/docker_compose/compose_text-generation.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -186,7 +186,7 @@ services:
ZE_AFFINITY_MASK: ${ZE_AFFINITY_MASK}
shm_size: 128g
entrypoint: /bin/bash -c "\
chmod +x /llm/vllm_ipex_entrypoint.sh && \
source /opt/intel/oneapi/setvars.sh --force && \
bash /llm/vllm_ipex_entrypoint.sh"

networks:
Expand Down
6 changes: 3 additions & 3 deletions comps/llms/src/text-generation/README_vllm_ipex.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -19,7 +19,7 @@ This service provides high-throughput, low-latency LLM serving accelerated by vL
You must download the official docker image from [Docker Hub](https://hub.docker.com/r/intel/llm-scaler-vllm) first.

```bash
docker pull intel/llm-scaler-vllm:1.0
docker pull intel/llm-scaler-vllm:0.10.0-b4
```

## Start Microservice
Expand All @@ -31,9 +31,9 @@ Deploy the vLLM-IPEX model serving using Docker Compose.
1. Export the required environment variables:

```bash
# Use image: intel/llm-scaler-vllm:1.0
# Use image: intel/llm-scaler-vllm:0.10.0-b4
export REGISTRY=intel
export TAG=1.0
export TAG=0.10.0-b4

export VIDEO_GROUP_ID=$(getent group video | awk -F: '{printf "%s\n", $3}')
export RENDER_GROUP_ID=$(getent group render | awk -F: '{printf "%s\n", $3}')
Expand Down
2 changes: 1 addition & 1 deletion comps/lvms/deployment/docker_compose/compose.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -188,7 +188,7 @@ services:
ZE_AFFINITY_MASK: ${ZE_AFFINITY_MASK}
shm_size: 128g
entrypoint: /bin/bash -c "\
chmod +x /llm/vllm_ipex_entrypoint.sh && \
source /opt/intel/oneapi/setvars.sh --force && \
bash /llm/vllm_ipex_entrypoint.sh"

networks:
Expand Down
6 changes: 3 additions & 3 deletions comps/lvms/src/README_vllm_ipex.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -19,7 +19,7 @@ This service provides high-throughput, low-latency LVM serving accelerated by vL
You must download the official docker image from [Docker Hub](https://hub.docker.com/r/intel/llm-scaler-vllm) first.

```bash
docker pull intel/llm-scaler-vllm:1.0
docker pull intel/llm-scaler-vllm:0.10.0-b4
```

## Start Microservice
Expand All @@ -31,9 +31,9 @@ Deploy the vLLM-IPEX model serving using Docker Compose.
1. Export the required environment variables:

```bash
# Use image: intel/llm-scaler-vllm:1.0
# Use image: intel/llm-scaler-vllm:0.10.0-b4
export REGISTRY=intel
export TAG=1.0
export TAG=0.10.0-b4

export ip_address=$(hostname -I | awk '{print $1}')
export VIDEO_GROUP_ID=$(getent group video | awk -F: '{printf "%s\n", $3}')
Expand Down
Loading