Upgrade vllm v0.18.0 in dockerfile (#7523)

### What this PR does / why we need it?
Upgrade vllm v0.18.0 in dockerfile

### Does this PR introduce _any_ user-facing change?

### How was this patch tested?

- vLLM version: v0.17.0
- vLLM main:
https://github.com/vllm-project/vllm/commit/8b6325758cce5f9c36d38f2462edbd368b97a07c

Signed-off-by: hfadzxy <starmoon_zhang@163.com>
This commit is contained in:
zhangxinyuehfad authored and GitHub committed 2026-03-21 16:19:41 +08:00
1 parent bff4fbfca5
commit f482c314cf
7 files changed
+7 -7

No files matched your search

+1 -1
View File
@@ -50,7 +50,7 @@ RUN yum update -y && \
# Install vLLM
ARG VLLM_REPO=https://github.com/vllm-project/vllm.git
ARG VLLM_TAG=v0.17.0
ARG VLLM_TAG=v0.18.0
RUN git clone --depth 1 $VLLM_REPO --branch $VLLM_TAG /vllm-workspace/vllm
# In x86, triton will be installed by vllm. But in Ascend, triton doesn't work correctly. we need to uninstall it.
RUN VLLM_TARGET_DEVICE="empty" python3 -m pip install -e /vllm-workspace/vllm/[audio] --extra-index https://download.pytorch.org/whl/cpu/ && \