Skip to content

Commit 97ffb91

Browse files
authored
[CI] Defaultly compile vllm with multimodal audio feature in dockerfile (#4324) (#4341)
### What this PR does / why we need it? For better usability, add multimodal audio to vllm compiling in dockerfile defaultly. Image size will increase only 2.xM. Signed-off-by: Ting FU <[email protected]>
1 parent 218bc70 commit 97ffb91

File tree

6 files changed

+6
-6
lines changed

6 files changed

+6
-6
lines changed

Dockerfile

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -40,7 +40,7 @@ ARG VLLM_REPO=https://github.com/vllm-project/vllm.git
4040
ARG VLLM_TAG=v0.11.0
4141
RUN git clone --depth 1 $VLLM_REPO --branch $VLLM_TAG /vllm-workspace/vllm
4242
# In x86, triton will be installed by vllm. But in Ascend, triton doesn't work correctly. we need to uninstall it.
43-
RUN VLLM_TARGET_DEVICE="empty" python3 -m pip install -v -e /vllm-workspace/vllm/ --extra-index https://download.pytorch.org/whl/cpu/ && \
43+
RUN VLLM_TARGET_DEVICE="empty" python3 -m pip install -v -e /vllm-workspace/vllm/[audio] --extra-index https://download.pytorch.org/whl/cpu/ && \
4444
python3 -m pip uninstall -y triton && \
4545
python3 -m pip cache purge
4646

Dockerfile.310p

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -40,7 +40,7 @@ ARG VLLM_REPO=https://github.com/vllm-project/vllm.git
4040
ARG VLLM_TAG=v0.11.0
4141
RUN git clone --depth 1 $VLLM_REPO --branch $VLLM_TAG /vllm-workspace/vllm
4242
# In x86, triton will be installed by vllm. But in Ascend, triton doesn't work correctly. we need to uninstall it.
43-
RUN VLLM_TARGET_DEVICE="empty" python3 -m pip install -v -e /vllm-workspace/vllm/ --extra-index https://download.pytorch.org/whl/cpu/ && \
43+
RUN VLLM_TARGET_DEVICE="empty" python3 -m pip install -v -e /vllm-workspace/vllm/[audio] --extra-index https://download.pytorch.org/whl/cpu/ && \
4444
python3 -m pip uninstall -y triton && \
4545
python3 -m pip cache purge
4646

Dockerfile.310p.openEuler

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -38,7 +38,7 @@ ARG VLLM_TAG=v0.11.0
3838

3939
RUN git clone --depth 1 $VLLM_REPO --branch $VLLM_TAG /vllm-workspace/vllm
4040
# In x86, triton will be installed by vllm. But in Ascend, triton doesn't work correctly. we need to uninstall it.
41-
RUN VLLM_TARGET_DEVICE="empty" python3 -m pip install -e /vllm-workspace/vllm/ --extra-index https://download.pytorch.org/whl/cpu/ && \
41+
RUN VLLM_TARGET_DEVICE="empty" python3 -m pip install -e /vllm-workspace/vllm/[audio] --extra-index https://download.pytorch.org/whl/cpu/ && \
4242
python3 -m pip uninstall -y triton && \
4343
python3 -m pip cache purge
4444

Dockerfile.a3

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -40,7 +40,7 @@ ARG VLLM_REPO=https://github.com/vllm-project/vllm.git
4040
ARG VLLM_TAG=v0.11.0
4141
RUN git clone --depth 1 $VLLM_REPO --branch $VLLM_TAG /vllm-workspace/vllm
4242
# In x86, triton will be installed by vllm. But in Ascend, triton doesn't work correctly. we need to uninstall it.
43-
RUN VLLM_TARGET_DEVICE="empty" python3 -m pip install -v -e /vllm-workspace/vllm/ --extra-index https://download.pytorch.org/whl/cpu/ && \
43+
RUN VLLM_TARGET_DEVICE="empty" python3 -m pip install -v -e /vllm-workspace/vllm/[audio] --extra-index https://download.pytorch.org/whl/cpu/ && \
4444
python3 -m pip uninstall -y triton && \
4545
python3 -m pip cache purge
4646

Dockerfile.a3.openEuler

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -38,7 +38,7 @@ ARG VLLM_TAG=v0.11.0
3838

3939
RUN git clone --depth 1 $VLLM_REPO --branch $VLLM_TAG /vllm-workspace/vllm
4040
# In x86, triton will be installed by vllm. But in Ascend, triton doesn't work correctly. we need to uninstall it.
41-
RUN VLLM_TARGET_DEVICE="empty" python3 -m pip install -e /vllm-workspace/vllm/ --extra-index https://download.pytorch.org/whl/cpu/ && \
41+
RUN VLLM_TARGET_DEVICE="empty" python3 -m pip install -e /vllm-workspace/vllm/[audio] --extra-index https://download.pytorch.org/whl/cpu/ && \
4242
python3 -m pip uninstall -y triton && \
4343
python3 -m pip cache purge
4444

Dockerfile.openEuler

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -38,7 +38,7 @@ ARG VLLM_TAG=v0.11.0
3838

3939
RUN git clone --depth 1 $VLLM_REPO --branch $VLLM_TAG /vllm-workspace/vllm
4040
# In x86, triton will be installed by vllm. But in Ascend, triton doesn't work correctly. we need to uninstall it.
41-
RUN VLLM_TARGET_DEVICE="empty" python3 -m pip install -e /vllm-workspace/vllm/ --extra-index https://download.pytorch.org/whl/cpu/ && \
41+
RUN VLLM_TARGET_DEVICE="empty" python3 -m pip install -e /vllm-workspace/vllm/[audio] --extra-index https://download.pytorch.org/whl/cpu/ && \
4242
python3 -m pip uninstall -y triton && \
4343
python3 -m pip cache purge
4444

0 commit comments

Comments
 (0)