diff --git a/docker/Dockerfile.npu b/docker/Dockerfile.npu index 47ea99fc7..2e961b89e 100644 --- a/docker/Dockerfile.npu +++ b/docker/Dockerfile.npu @@ -1,20 +1,20 @@ ARG VLLM_ASCEND_IMAGE=quay.io/ascend/vllm-ascend -ARG VLLM_ASCEND_TAG=v0.17.0rc1 +ARG VLLM_ASCEND_TAG=v0.18.0rc1 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 +# 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=$LD_LIBRARY_PATH:/usr/local/Ascend/ascend-toolkit/latest/`uname -i`-linux/devlib && \ - python3 -m pip install -v -e /vllm-workspace/vllm-ascend/ --extra-index https://download.pytorch.org/whl/cpu/ && \ - python3 -m pip cache purge +# WORKDIR /vllm-workspace/vllm-ascend +# RUN git fetch origin releases/v0.18.0 && git checkout d781902ce9dbda8ab1e11bb0f2f0c1bc508fee7a +# # Install vllm-ascend +# # Append `libascend_hal.so` path (devlib) to LD_LIBRARY_PATH +# RUN export PIP_EXTRA_INDEX_URL=https://mirrors.huaweicloud.com/ascend/repos/pypi && \ +# source /usr/local/Ascend/ascend-toolkit/set_env.sh && \ +# source /usr/local/Ascend/nnal/atb/set_env.sh && \ +# export LD_LIBRARY_PATH=$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} diff --git a/docker/Dockerfile.npu.a3 b/docker/Dockerfile.npu.a3 index e91938257..e3781fc18 100644 --- a/docker/Dockerfile.npu.a3 +++ b/docker/Dockerfile.npu.a3 @@ -1,20 +1,20 @@ ARG VLLM_ASCEND_IMAGE=quay.io/ascend/vllm-ascend -ARG VLLM_ASCEND_TAG=v0.17.0rc1-a3 +ARG VLLM_ASCEND_TAG=v0.18.0rc1-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 +# 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=$LD_LIBRARY_PATH:/usr/local/Ascend/ascend-toolkit/latest/`uname -i`-linux/devlib && \ - python3 -m pip install -v -e /vllm-workspace/vllm-ascend/ --extra-index https://download.pytorch.org/whl/cpu/ && \ - python3 -m pip cache purge +# WORKDIR /vllm-workspace/vllm-ascend +# RUN git fetch origin releases/v0.18.0 && git checkout d781902ce9dbda8ab1e11bb0f2f0c1bc508fee7a +# # Install vllm-ascend +# # Append `libascend_hal.so` path (devlib) to LD_LIBRARY_PATH +# RUN export PIP_EXTRA_INDEX_URL=https://mirrors.huaweicloud.com/ascend/repos/pypi && \ +# source /usr/local/Ascend/ascend-toolkit/set_env.sh && \ +# source /usr/local/Ascend/nnal/atb/set_env.sh && \ +# export LD_LIBRARY_PATH=$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} diff --git a/docs/getting_started/installation/npu/npu.inc.md b/docs/getting_started/installation/npu/npu.inc.md index b718bd493..c5b13dd73 100644 --- a/docs/getting_started/installation/npu/npu.inc.md +++ b/docs/getting_started/installation/npu/npu.inc.md @@ -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:v0.17.0rc1 +# export IMAGE=quay.io/ascend/vllm-ascend:v0.18.0rc1 # Atlas A3: -# export IMAGE=quay.io/ascend/vllm-ascend:v0.17.0rc1-a3 -export IMAGE=quay.io/ascend/vllm-ascend:v0.17.0rc1 +# export IMAGE=quay.io/ascend/vllm-ascend:v0.18.0rc1-a3 +export IMAGE=quay.io/ascend/vllm-ascend:v0.18.0rc1 docker run --rm \ --name vllm-omni-npu \ --shm-size=1g \ @@ -33,17 +33,6 @@ docker run --rm \ -p 8000:8000 \ -it $IMAGE bash -cd /vllm-workspace/vllm -git fetch origin --tags -git checkout v0.18.0 - -# 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 d781902ce9dbda8ab1e11bb0f2f0c1bc508fee7a -pip install -v -e . - # Inside the container, install vLLM-Omni from source cd /vllm-workspace git clone -b v0.18.0 https://github.com/vllm-project/vllm-omni.git @@ -68,15 +57,10 @@ 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 fetch origin --tags -git checkout v0.18.0 +git clone -b v0.18.0 https://github.com/vllm-project/vllm.git +VLLM_TARGET_DEVICE=empty pip install -v -e . -# Because vllm-ascend has not yet entered continuous development and has not been officially released, we need to pin it to a specific commit. Please note that this commit may change over time. -cd /vllm-workspace/vllm-ascend -git pull origin main -git fetch origin --tags -git checkout d781902ce9dbda8ab1e11bb0f2f0c1bc508fee7a +git clone -b v0.18.0rc1 https://github.com/vllm-project/vllm-ascend.git pip install -v -e . # Install vLLM-Omni from the latest main branch