diff --git a/docker/Dockerfile-NPU b/docker/Dockerfile-NPU index 270a63c95..5fb3da5e7 100644 --- a/docker/Dockerfile-NPU +++ b/docker/Dockerfile-NPU @@ -1,5 +1,5 @@ # Set to other image if needed -FROM quay.io/ascend/vllm-ascend:v0.9.2rc1 +FROM quay.io/ascend/vllm-ascend:v0.9.2rc1-openeuler ARG PIP_INDEX_URL="https://mirrors.tuna.tsinghua.edu.cn/pypi/web/simple" @@ -14,4 +14,12 @@ RUN export PLATFORM="ascend" && \ export LD_LIBRARY_PATH=$LD_LIBRARY_PATH:/usr/local/Ascend/ascend-toolkit/latest/`uname -i`-linux/devlib && \ pip install -v -e /workspace/unified-cache-management --no-build-isolation +# Apply patch for vLLM +RUN cd /vllm-workspace/vllm \ + && git apply /workspace/unified-cache-management/ucm/integration/vllm/patch/0.9.2/vllm-adapt.patch + +# Apply patch for vLLM-ascend +RUN cd /vllm-workspace/vllm-ascend \ + && git apply /workspace/unified-cache-management/ucm/integration/vllm/patch/0.9.2/vllm-ascend-adapt.patch + CMD ["/bin/bash"] \ No newline at end of file diff --git a/docs/source/getting-started/quickstart_vllm_ascend.md b/docs/source/getting-started/quickstart_vllm_ascend.md index 0c51d57e6..85a4bdd20 100644 --- a/docs/source/getting-started/quickstart_vllm_ascend.md +++ b/docs/source/getting-started/quickstart_vllm_ascend.md @@ -41,6 +41,14 @@ Download the pre-built `vllm-ascend` docker image and build unified-cache-manage cd unified-cache-management docker build -t ucm-vllm:latest -f ./docker/Dockerfile-NPU ./ ``` +vllm-ascend provides two variants: **Ubuntu** and **openEuler**. +The `Dockerfile-NPU` uses the **openEuler** variant by default. + +If you want to use the **Ubuntu** variant, please remove the `-openeuler` suffix and use the following image instead: + +```text +quay.io/ascend/vllm-ascend:v0.9.2rc1 +``` Then run your container using following command. You can add or remove Docker parameters as needed. ```bash # Update DEVICE according to your device (/dev/davinci[0-7])