anodyine/vllm-omni
1
0 Fork 0
Code Issues 4 Pull Requests 2 Actions Packages Projects Releases Wiki Activity

[Release] Upgrade NPU dockerfile & docs for v0.18.0 (#2271)

Browse Source
This commit is contained in:
Canlin Guo authored and GitHub committed 2026-03-27 20:37:16 +08:00
1 parent 637abb759f
commit 3fe46360f0
3 files changed
+39 -15
Download Patch File Download Diff File Expand all files Collapse all files

No files matched your search

docker/Dockerfile.npu
+14 -1
View File
@@ -2,9 +2,22 @@ ARG VLLM_ASCEND_IMAGE=quay.io/ascend/vllm-ascend
ARG VLLM_ASCEND_TAG=v0.17.0rc1
FROM ${VLLM_ASCEND_IMAGE}:${VLLM_ASCEND_TAG}
WORKDIR /vllm-workspace/vllm
RUN git fetch origin --tags && git checkout v0.18.0
WORKDIR /vllm-workspace/vllm-ascend
RUN git fetch origin releases/v0.18.0 && git checkout d781902ce9dbda8ab1e11bb0f2f0c1bc508fee7a
# Install vllm-ascend
# Append `libascend_hal.so` path (devlib) to LD_LIBRARY_PATH
RUN export PIP_EXTRA_INDEX_URL=https://mirrors.huaweicloud.com/ascend/repos/pypi && \
source /usr/local/Ascend/ascend-toolkit/set_env.sh && \
source /usr/local/Ascend/nnal/atb/set_env.sh && \
export LD_LIBRARY_PATH=$LD_LIBRARY_PATH:/usr/local/Ascend/ascend-toolkit/latest/`uname -i`-linux/devlib && \
python3 -m pip install -v -e /vllm-workspace/vllm-ascend/ --extra-index https://download.pytorch.org/whl/cpu/ && \
python3 -m pip cache purge
ARG APP_DIR=/vllm-workspace/vllm-omni
WORKDIR ${APP_DIR}
COPY . .
RUN export PIP_EXTRA_INDEX_URL=https://mirrors.huaweicloud.com/ascend/repos/pypi && \
docker/Dockerfile.npu.a3
+14 -1
View File
@@ -2,9 +2,22 @@ ARG VLLM_ASCEND_IMAGE=quay.io/ascend/vllm-ascend
ARG VLLM_ASCEND_TAG=v0.17.0rc1-a3
FROM ${VLLM_ASCEND_IMAGE}:${VLLM_ASCEND_TAG}
WORKDIR /vllm-workspace/vllm
RUN git fetch origin --tags && git checkout v0.18.0
WORKDIR /vllm-workspace/vllm-ascend
RUN git fetch origin releases/v0.18.0 && git checkout d781902ce9dbda8ab1e11bb0f2f0c1bc508fee7a
# Install vllm-ascend
# Append `libascend_hal.so` path (devlib) to LD_LIBRARY_PATH
RUN export PIP_EXTRA_INDEX_URL=https://mirrors.huaweicloud.com/ascend/repos/pypi && \
source /usr/local/Ascend/ascend-toolkit/set_env.sh && \
source /usr/local/Ascend/nnal/atb/set_env.sh && \
export LD_LIBRARY_PATH=$LD_LIBRARY_PATH:/usr/local/Ascend/ascend-toolkit/latest/`uname -i`-linux/devlib && \
python3 -m pip install -v -e /vllm-workspace/vllm-ascend/ --extra-index https://download.pytorch.org/whl/cpu/ && \
python3 -m pip cache purge
ARG APP_DIR=/vllm-workspace/vllm-omni
WORKDIR ${APP_DIR}
COPY . .
RUN export PIP_EXTRA_INDEX_URL=https://mirrors.huaweicloud.com/ascend/repos/pypi && \
docs/getting_started/installation/npu/npu.inc.md
+11 -13
View File
@@ -10,10 +10,10 @@ The recommended way to use vLLM-Omni on NPU is through the vllm-ascend pre-built
```bash
# Update the vllm-ascend image
# Atlas A2:
# export IMAGE=quay.io/ascend/vllm-ascend:v0.14.0rc1
# export IMAGE=quay.io/ascend/vllm-ascend:v0.17.0rc1
# Atlas A3:
# export IMAGE=quay.io/ascend/vllm-ascend:v0.14.0rc1-a3
export IMAGE=quay.io/ascend/vllm-ascend:v0.14.0rc1
# export IMAGE=quay.io/ascend/vllm-ascend:v0.17.0rc1-a3
export IMAGE=quay.io/ascend/vllm-ascend:v0.17.0rc1
docker run --rm \
--name vllm-omni-npu \
--shm-size=1g \
@@ -34,20 +34,19 @@ docker run --rm \
-it $IMAGE bash
cd /vllm-workspace/vllm
git pull origin main
git fetch origin --tags
git checkout v0.16.0
git checkout v0.18.0
# Because vllm-ascend will release v0.16.0rc1 after vllm-omni 0.16.0,
# Because vllm-ascend will release v0.18.0rc1 after vllm-omni 0.16.0,
# we have to pin vllm-ascend at the current commit.
cd /vllm-workspace/vllm-ascend
git pull origin main
git checkout e2175d9c7e62b437391dfee996b1375674ba7c18
git checkout d781902ce9dbda8ab1e11bb0f2f0c1bc508fee7a
pip install -v -e .
# Inside the container, install vLLM-Omni from source
cd /vllm-workspace
git clone -b v0.16.0 https://github.com/vllm-project/vllm-omni.git
git clone -b v0.18.0 https://github.com/vllm-project/vllm-omni.git
cd vllm-omni
pip install -v -e . --no-build-isolation
# or VLLM_OMNI_TARGET_DEVICE=npu pip install -v -e .
@@ -70,7 +69,6 @@ You can also build vLLM-Omni from the latest main branch if you want to use the
```bash
# Pin vLLM version to 0.18.0
cd /vllm-workspace/vllm
git pull origin main
git fetch origin --tags
git checkout v0.18.0
@@ -78,7 +76,7 @@ git checkout v0.18.0
cd /vllm-workspace/vllm-ascend
git pull origin main
git fetch origin --tags
git checkout 1e05c4908f31737bc4eef865a9f351d030a77c9d
git checkout d781902ce9dbda8ab1e11bb0f2f0c1bc508fee7a
pip install -v -e .
# Install vLLM-Omni from the latest main branch
@@ -106,10 +104,10 @@ Here's an example deployment command that has been verified on 4 x NPUs:
```bash
# Atlas A2:
# export IMAGE=quay.io/ascend/vllm-omni:v0.16.0
# export IMAGE=quay.io/ascend/vllm-omni:v0.18.0
# Atlas A3:
# export IMAGE=quay.io/ascend/vllm-omni:v0.16.0-a3
export IMAGE=quay.io/ascend/vllm-omni:v0.16.0
# export IMAGE=quay.io/ascend/vllm-omni:v0.18.0-a3
export IMAGE=quay.io/ascend/vllm-omni:v0.18.0
docker run --rm \
--name vllm-omni-npu \
--shm-size=1g \